get_adcp_capabilities

get_adcp_capabilities is the first call a buyer makes to discover an AdCP seller’s supported protocols, auth model, version, and feature capabilities. Request and response schema reference.

Discover a seller’s protocol support and capabilities across all AdCP protocols. This is the first call a buyer should make to understand what a seller supports.

Why this shape. Capabilities are organized into ~14 top-level domain keys (one per protocol plus identity and signing infrastructure), with feature flags nested under each domain’s features/execution/etc. sub-namespace. We rejected a flat capability list — it forces every implementer to scan an unbounded surface, and it removes the discoverability that comes from related flags sitting next to each other. New capability flags belong under existing domains, not in new top-level keys; declarations are commitments, not advertisements (the conformance runner probes them). → Capabilities explorer walks the tree before you propose. → Design principle: capabilities are commitments.

Response Time: ~2 seconds (configuration lookup)

Purpose:

• AdCP discovery - Does this agent support AdCP? Which versions?
• Protocol support - Which protocols (media_buy, signals, governance, sponsored_intelligence, creative, brand)?
• Auth model - Does this seller trust the agent directly, or must each operator authenticate independently?
• Detailed capabilities - Features, execution integrations, geo targeting, portfolio

Per-caller authorization is NOT reported here. get_adcp_capabilities returns the seller’s surface — everything it could do for any authorized caller. To discover what you are allowed to do on a specific account (which tasks are callable for your identity, which request fields are modifiable, any named scope like attestation_verifier), read the authorization object on per-account entries in sync_accounts and list_accounts responses. See Caller authorization for the full shape and semantics.

Request Schema: /schemas/v3/protocol/get-adcp-capabilities-request.json Response Schema: /schemas/v3/protocol/get-adcp-capabilities-response.json

Tool-Based Discovery

AdCP uses native MCP/A2A tool discovery. The presence of get_adcp_capabilities in an agent’s tool list indicates AdCP support.

Discovery Flow:
1. Browse agent's tool list (MCP) or skills (A2A)
2. See 'get_adcp_capabilities' tool → Agent supports AdCP
3. Call get_adcp_capabilities → Get version, protocols, features, capabilities
4. Proceed based on returned capabilities

This approach:

• Uses standard MCP/A2A mechanisms (no custom extensions)
• Always returns current capabilities (not stale metadata)
• Single source of truth for all capability information

:::note The agent card extension (adcp-extension.json) has been removed in v3. Use tool-based discovery instead. :::

Version Negotiation

Sellers declare which major versions they support via adcp.major_versions in the response. Buyers declare which version they’re using via adcp_major_version on the request.

Version Negotiation Flow:
1. Buyer calls get_adcp_capabilities with adcp_major_version: 2
2. Seller checks 2 against its major_versions: [2, 3]
3. Version is supported → seller returns capabilities for v2
4. Buyer includes adcp_major_version: 2 on all subsequent requests

adcp_major_version is an optional field on every AdCP request schema. Buyers SHOULD include it on all requests when interacting with a multi-version seller.

Seller behavior:

• If adcp_major_version is provided and supported → respond using that version’s schemas
• If adcp_major_version is provided but unsupported → return VERSION_UNSUPPORTED (buyer should call without adcp_major_version to discover supported versions)
• If adcp_major_version is omitted → assume the highest supported version

Why major versions, not minor? Semver policy guarantees backward compatibility within a major version. A seller at 3.1 can serve a buyer at 3.0 without negotiation. The capability model handles feature-level differences — buyers check specific capabilities (targeting systems, features, extensions) rather than version numbers to determine compatibility.

Request Parameters

Field	Type	Description
adcp_major_version	integer	Optional. The AdCP major version the buyer’s payloads conform to. When provided, the seller validates against its major_versions and returns VERSION_UNSUPPORTED if not in range. When omitted, the seller assumes the highest major version it supports.
protocols	string[]	Optional. Filter to specific protocols (media_buy, signals, governance, sponsored_intelligence, creative, brand). If omitted, returns all supported protocols.

Response Structure

adcp

Core AdCP protocol information:

Field	Type	Description
major_versions	integer[]	Required. AdCP major versions supported (e.g., [3])
idempotency	object	Required. Idempotency semantics. See idempotency.

idempotency

Declares whether this seller honors idempotency_key replay protection. From 3.1 onward idempotency_key is required on every AdCP task request (read and mutating alike — staged enforcement for reads: SHOULD-reject in 3.1, MUST-reject in 3.2; see security.mdx § Idempotency). Mirrors the request_signing.supported pattern — a single positive declaration, decoupled from the window detail. Clients MUST NOT assume a default; a seller without this block is non-compliant and should be treated as unsafe for retry-sensitive operations across all call modes.

Field	Type	Description
supported	boolean	Required. Whether the seller deduplicates replays. When false, sending an idempotency_key is a no-op — the seller will NOT return IDEMPOTENCY_CONFLICT or IDEMPOTENCY_EXPIRED, and a naive retry WILL double-process. Buyers MUST use natural-key checks (e.g., get_media_buys plus request context such as context.internal_campaign_id or package context such as context.buyer_ref) before retrying spend-committing operations.
replay_ttl_seconds	integer	Required when supported: true. How long the seller retains a canonical response for a key. Minimum 3600 (1h); recommended 86400 (24h); maximum 604800 (7d).

{
  "adcp": {
    "major_versions": [3],
    "idempotency": { "supported": true, "replay_ttl_seconds": 86400 }
  }
}

Sellers that do not support replay dedup declare it explicitly:

{
  "adcp": {
    "major_versions": [3],
    "idempotency": { "supported": false }
  }
}

Verifying the declaration. idempotency.supported: true is a trust-bearing claim that enables buyers to safely retry spend-committing operations. A compromised or buggy seller could advertise true while silently ignoring keys, causing buyer double-spend on retry. Buyers and conformance runners SHOULD probe the declaration with a deliberate payload-mutation replay: send two requests with the same idempotency_key but different canonical payloads — a conformant seller MUST return IDEMPOTENCY_CONFLICT on the second. Sellers declaring supported: true MUST pass this probe as part of the baseline compliance storyboard before the declaration is considered verified.

supported_protocols

AdCP protocols this agent supports. This is the single capability axis — each value both (a) declares which tools the agent implements and (b) commits the agent to pass the baseline compliance storyboard at /compliance/{version}/protocols/{protocol}/. The runner maps JSON snake_case → URL kebab-case (media_buy → /compliance/.../protocols/media-buy/).

{
  "supported_protocols": ["media_buy", "creative"]
}

Valid values: media_buy, creative, signals, governance, brand, sponsored_intelligence.

See the Compliance Catalog for every protocol’s scope. Support for the compliance test controller is declared via the separate compliance_testing capability block (below), not as a protocol value.

specialisms

Optional specialization claims. Each entry corresponds to a narrow storyboard at /compliance/{version}/specialisms/{id}/. Every specialism rolls up to one protocol in supported_protocols — claiming sales-guaranteed requires media_buy. The runner rejects a specialism whose parent protocol is missing.

{
  "specialisms": ["sales-guaranteed", "creative-template"]
}

See the full Compliance Catalog for every specialism and the enum schema for the authoritative list.

Capability slot gaps

SDK helpers such as definePlatform can project a platform implementation into narrower capability slots. Treat those slots as commitments: only declare a slot when the agent can execute the corresponding task path end to end.

If a storyboard or local test vector targets a slot the agent does not declare, the expected conformance outcome is not_applicable, not failure. Until runner-side enforcement lands in adcp-client#2244, implementers running custom or prerelease suites should add explicit skip gates for vectors outside the declared slot scope. Do not work around a missing slot by declaring it and returning placeholder responses; that turns an honest coverage gap into a failed capability claim.

account

Account and authentication capabilities. All sellers should declare this section — buyers read it before calling sync_accounts, list_accounts, or any authenticated task. Even simple publishers need account management to handle billing relationships and sandbox testing.

Field	Type	Description
supported_billing	string[]	Required. Billing models this seller supports: operator, agent. The buyer must pass one of these values as billing in every sync_accounts entry.
require_operator_auth	boolean	Default: false. Declares who must authenticate; it does not by itself declare whether OAuth is used, whether list_accounts is exposed, or which sync_accounts modes are supported. When true, each operator authenticates independently and account-scoped calls use seller-assigned account_id values because the seller or upstream platform owns the canonical account namespace. If a credential may access more than one account, the seller MUST expose list_accounts and buyers MUST resolve an explicit account_id before the first account-scoped request. If a credential is bound to exactly one account, the seller SHOULD expose list_accounts returning that singleton; a seller MAY omit list_accounts only when it provides the same explicit account_id through another declared path or out-of-band onboarding. When false, the agent is trusted, buyer declares accounts via sync_accounts, and subsequent calls pass the natural key (brand + operator). For sandbox, account-id namespaces use pre-existing test accounts from list_accounts or out-of-band setup; buyer-declared accounts use sync_accounts with sandbox: true.
authorization_endpoint	string	OAuth URL for operator authentication. Present when the seller supports OAuth for operator authentication. Relevant when require_operator_auth: true; if absent, operators obtain credentials out-of-band (seller portal, API key).
required_for_products	boolean	Default: false. When true, the buyer must establish an account before calling get_products. When false, the buyer can browse products without an account — useful for price comparison and discovery before committing to a seller.
account_financials	boolean	Default: false. When true, the seller supports get_account_financials for querying spend, credit, and invoice status. Only applicable to operator-billed accounts.
sandbox	boolean	Default: false. Strongly recommended for production sales agents. When true, the seller supports sandbox accounts for testing. For sandbox, account-id namespaces discover pre-existing test accounts through list_accounts or out-of-band setup; buyer-declared accounts declare sandbox via sync_accounts with sandbox: true — no real platform calls or spend. See Sandbox mode.

Auth models

Buyer-declared accounts (require_operator_auth: false) — The seller trusts the agent’s identity claims. The agent authenticates once with its own bearer token, then calls sync_accounts to declare which brands and operators it represents. The seller provisions accounts based on the agent’s claims, optionally verifying operators against brand.json. All subsequent calls use the agent’s single credential and pass natural keys (brand + operator).

Account-id namespaces (require_operator_auth: true) — Each operator must authenticate with the seller directly. The agent obtains a credential per operator — via OAuth using authorization_endpoint, or out-of-band — opens a per-operator session, and passes seller-assigned account_id values on subsequent requests. OAuth is credential acquisition, not an account taxonomy axis. Two namespace patterns use the same wire reference: upstream-managed sellers expose list_accounts, making explicit account resolution mandatory before account-scoped calls; seller-defined namespaces without list_accounts provide account IDs out-of-band. SDKs SHOULD lazily call list_accounts when first needed, auto-select a singleton, cache it per credential/session, and still send explicit AccountRef values on required-account calls.

For sandbox, the path follows the account namespace: account-id namespaces discover pre-existing test accounts via list_accounts or out-of-band setup; buyer-declared accounts declare sandbox via sync_accounts with sandbox: true.

See Accounts and Agents for full workflows and seller patterns for common combinations of auth model and billing support.

media_buy

Media-buy protocol capabilities. Only present if media_buy is in supported_protocols. Sellers declaring media_buy should also include account (with supported_billing) and media_buy.portfolio — buyers need both to establish billing and understand inventory coverage. Compliance testing validates their presence.

:::note 3.0 breaking changes The following fields have been removed from the capabilities response:

• media_buy.reporting — Reporting is implied by media_buy. Use product-level reporting_capabilities instead.
• features.content_standards — Replaced by media_buy.content_standards object. Presence of the object indicates support.
• features.audience_targeting — Replaced by media_buy.audience_targeting object. Presence of the object indicates support.
• features.conversion_tracking — Replaced by media_buy.conversion_tracking object. Presence of the object indicates support.
• execution.targeting.device_platform, device_type — Implied by media_buy support.
• execution.targeting.audience_include, audience_exclude — Implied by audience_targeting object presence.
• execution.trusted_match.supported — Object presence indicates support.
• brand.identity — Implied by brand in supported_protocols. get_brand_identity is always available. :::

reporting_delivery_methods

Declares which push-based delivery methods are available across the seller’s product portfolio. Polling via get_media_buy_delivery is a required task for all media_buy sellers regardless of this field.

Method	Description	Configuration
webhook	Seller pushes to buyer-provided URL	Buyer configures reporting_webhook per media buy
offline	Seller pushes batch files to a cloud storage bucket	Seller provisions reporting_bucket per account

When absent, only polling is available. Cadence and metrics are declared per product in reporting_capabilities.

When offline is declared, also include offline_delivery_protocols to declare which cloud storage protocols are supported (s3, gcs, azure_blob). Buyers express a protocol preference via preferred_reporting_protocol in sync_accounts; the seller provisions the account’s reporting_bucket using a supported protocol.

For offline delivery, the seller provisions a per-account bucket and grants the buyer read access out-of-band. The bucket location (including file_retention_days) appears on the account object returned by sync_accounts as reporting_bucket. See Offline File Delivery for details.

creative_approval_mode

Declares the seller’s tenant-wide creative approval posture after creatives are assigned and automated validation passes. This is not a notification surface or a new approval workflow; it tells buyers and compliance runners whether human review can still block serving eligibility. Compliance runners use this declaration mainly to decide whether auto-approval-dependent storyboards such as media_buy_seller/pending_creatives_to_start apply.

Value	Description
auto_approve	Human review does not block serving eligibility after creatives are assigned and automated validation passes. Auto-approval-dependent storyboards can run.
require_human	One or more products/accounts may require manual review before creatives become eligible to serve. Treat this as a tenant-wide worst-case ceiling until a product-level override exists.

Sellers with mixed approval policies SHOULD declare require_human unless every product/account that can be reached by the advertised agent supports automatic eligibility after automated validation. When the field is absent, approval behavior is legacy-unspecified; runners SHOULD NOT treat omission as an affirmative auto_approve claim. ai_assisted is intentionally not a value until the protocol defines what assistance changes in observable behavior.

features

Optional media-buy features. If declared true, seller MUST honor requests using that feature.

Feature	Description
inline_creative_management	Accepts creatives inline in create_media_buy and update_media_buy package payloads
property_list_filtering	Honors property_list parameter in get_products
catalog_management	Supports sync_catalogs for catalog feed management

content_standards

Content standards implementation details. Presence of this object indicates the seller supports content_standards configuration including sampling rates and category filtering. Gives buyers pre-buy visibility into local evaluation and artifact delivery capabilities.

Field	Type	Description
supports_local_evaluation	boolean	Whether the seller runs a local evaluation model. When false, local_verdict will always be unevaluated and the failures_only filter on get_media_buy_artifacts is not useful.
supported_channels	string[]	Channels for which the seller can provide content artifacts. Helps buyers understand which parts of a mixed-channel buy will have content standards coverage.
supports_webhook_delivery	boolean	Whether the seller supports push-based artifact delivery via artifact_webhook configured at buy creation time.

Example:

{
  "content_standards": {
    "supports_local_evaluation": true,
    "supported_channels": ["display", "olv", "podcast"],
    "supports_webhook_delivery": true
  }
}

If supports_local_evaluation is false, the failures_only filter on get_media_buy_artifacts will return an empty result set — all verdicts will be unevaluated.

execution

Technical execution capabilities:

Field	Type	Description
trusted_match	object	TMP support. When present, this seller supports real-time contextual and/or identity matching. Check individual products for per-product TMP capabilities.
axe_integrations	string[]	Deprecated. Legacy AXE URLs this seller can execute through. Use trusted_match for new integrations.
creative_specs	object	Creative specification support (VAST versions, MRAID, etc.)
targeting	object	Targeting capabilities (geo granularity)

axe_integrations

axe_integrations is an array of Agentic Ad Exchange (AXE) endpoint URLs that this seller can execute through. AXE is the real-time execution layer for AdCP campaigns — it connects buyer agents to programmatic inventory via standardized exchanges.

When a seller declares AXE URLs in their capabilities, buyers can:

• Route impression-level execution through the declared exchange
• Use the exchange’s targeting, optimization, and measurement capabilities
• Execute alongside the seller’s direct-sold inventory

Buyers discover AXE support via get_adcp_capabilities and filter products to AXE-enabled sellers using required_axe_integrations on get_products.

creative_specs

Field	Type	Description
vast_versions	string[]	VAST versions supported (e.g., ["4.0", "4.1", "4.2"])
mraid_versions	string[]	MRAID versions supported
vpaid	boolean	VPAID support
simid	boolean	SIMID support

targeting

Field	Type	Description
geo_countries	boolean	Country-level targeting using ISO 3166-1 alpha-2 codes
geo_regions	boolean	Region/state-level targeting using ISO 3166-2 codes (e.g., US-NY, GB-SCT)
geo_metros	object	Metro area targeting with system-specific support
geo_postal_areas	object	Postal area targeting with country and precision support
age_restriction	object	Age restriction capabilities with supported flag and verification_methods
language	boolean	Language targeting (ISO 639-1 codes)
keyword_targets	object	Keyword targeting with supported_match_types array (broad, phrase, exact). Presence indicates support.
negative_keywords	object	Negative keyword targeting with supported_match_types array. Presence indicates support.
geo_proximity	object	Proximity targeting from arbitrary coordinates (see below)

Device platform and device type targeting are implied by media_buy support. Audience include/exclude targeting is implied by the presence of the audience_targeting capabilities object.

Sellers that support a geographic targeting level SHOULD support both inclusion and exclusion at that level. For example, geo_metros.nielsen_dma: true SHOULD mean the seller supports both geo_metros and geo_metros_exclude with Nielsen DMA codes. If a seller only supports one direction (e.g., inclusion but not exclusion), it MUST return a validation error for unsupported fields rather than silently ignoring them. See Targeting Overlays for exclusion semantics.

geo_proximity specifies which proximity targeting methods are supported:

Field	Type	Description
radius	boolean	Simple radius targeting (distance circle from a point)
travel_time	boolean	Travel time isochrone targeting (requires a routing engine)
geometry	boolean	Pre-computed GeoJSON geometry (buyer provides the polygon)
transport_modes	string[]	Transport modes supported for isochrones: driving, walking, cycling, public_transport

geo_metros specifies which metro classification systems are supported:

System	Description
nielsen_dma	Nielsen DMA codes (US market, e.g., 501 for NYC)
uk_itl1	UK ITL Level 1 regions
uk_itl2	UK ITL Level 2 regions
eurostat_nuts2	Eurostat NUTS Level 2 regions (EU)

geo_postal_areas specifies which country-local postal code systems are supported. The preferred shape is keyed by ISO 3166-1 alpha-2 country, with each country listing supported systems:

{
  "us_zip": true,
  "us_zip_plus_four": true,
  "US": ["zip", "zip_plus_four"],
  "GB": ["outward", "full"],
  "CA": ["fsa", "full"],
  "ZA": ["postal_code"]
}

Use postal_code for the normal postal code string in countries without a more specific registered local system. During the 3.x migration, sellers SHOULD emit equivalent deprecated aliases such as us_zip alongside native country keys where an alias exists. Buyers and SDKs SHOULD normalize both shapes before making capability decisions.

audience_targeting

Audience targeting capabilities. Presence of this object indicates the seller supports audience targeting, including sync_audiences and audience_include/audience_exclude in targeting overlays. Describes what identifier types the seller accepts for audience matching, size constraints, and expected matching latency.

Field	Type	Required	Description
supported_identifier_types	string[]	Required	PII-derived identifier types accepted for audience matching. Buyers should only send identifiers the seller supports. Values: hashed_email, hashed_phone.
minimum_audience_size	integer	Required	Minimum matched audience size required for targeting. Audiences below this threshold will have status: too_small. Varies by platform (100–1000 is typical).
supports_platform_customer_id	boolean		When true, the seller accepts the buyer’s CRM/loyalty ID as a matchable identifier. Only applicable when the seller operates a closed ecosystem with a shared ID namespace (e.g., a retailer matching against their loyalty program). Buyers can include platform_customer_id values in AudienceMember.identifiers. Reporting on matched IDs typically requires a clean room or the seller’s own reporting surface.
supported_uid_types	string[]		Universal ID types accepted for audience matching (MAIDs, RampID, UID2, etc.). MAID support varies significantly by platform — check this field before sending uids with type: maid.
matching_latency_hours	object		Expected matching latency range in hours after upload. Use to calibrate polling cadence and set appropriate expectations before configuring push_notification_config. Shape: { min: integer, max: integer }.

conversion_tracking

Seller-level conversion tracking capabilities. Declares what the seller supports for kind: "event" optimization goals.

Field	Type	Description
multi_source_event_dedup	boolean	Whether the seller can deduplicate events across multiple event sources within a single goal. When true, the same event_id from multiple sources counts once. When false or absent, buyers should use a single event source per goal.
supported_event_types	string[]	Event types this seller can track. If omitted, all standard event types are supported.
supported_uid_types	string[]	Universal ID types accepted for user matching.
supported_hashed_identifiers	string[]	Hashed PII types accepted (hashed_email, hashed_phone). Buyers must hash before sending (SHA-256, normalized).
supported_action_sources	string[]	Action sources this seller accepts events from.
attribution_windows	object[]	Available attribution windows. Single-element arrays indicate fixed windows; multi-element arrays indicate configurable options the buyer can choose from via attribution_window on optimization goals.

portfolio

Inventory portfolio information:

Field	Type	Description
publisher_domains	string[]	Required. Publisher domains this seller represents
primary_channels	string[]	Main advertising channels
primary_countries	string[]	Main countries (ISO codes)
description	string	Markdown portfolio description
advertising_policies	string	Content policies and restrictions

signals

Signals protocol capabilities. Only present if signals is in supported_protocols.

Field	Type	Description
data_provider_domains	string[]	Data provider domains this signals agent is authorized to resell. Buyers should fetch each provider’s adagents.json for signal definitions and to verify authorization.
discovery_modes	string[]	Discovery modes the agent supports on get_signals. "brief" (semantic discovery via signal_spec / signal_refs, with deprecated signal_ids accepted for older clients) is implicit and always supported. Declare "wholesale" to advertise that callers can omit signal_spec / signal_refs / signal_ids and enumerate the full priced signals feed. Agents not declaring "wholesale" MAY return INVALID_REQUEST for wholesale calls. Absent declaration is treated as ["brief"].
features.catalog_signals	boolean	Deprecated. Legacy wire flag for structured signal_ref references to provider-published signal definitions in adagents.json signals[].

catalog_signals is deprecated. Existing 3.x agents may continue to emit it for compatibility, but new agents SHOULD omit it and callers MUST NOT require it before using signal_ref. Treat supported_protocols: ["signals"], signals.data_provider_domains, signals.discovery_modes, and the actual get_signals response as the capability surface.

creative

Creative protocol capabilities. Only present if creative is in supported_protocols.

Field	Type	Description
supports_compliance	boolean	When true, this creative agent can process briefs with compliance requirements (required_disclosures, prohibited_claims) and will validate that disclosures can be satisfied by the target format. Use the disclosure_positions filter on list_creative_formats to find compatible formats.
supports_transformers	boolean	When true, this creative agent offers account-scoped transformers — the selectable units of build capability (voices, models, styles) discovered via list_transformers and selected with transformer_id (plus the typed config bag) on build_creative. When false or absent, the agent does not expose transformers; list_transformers is unavailable and build_creative ignores transformer_id/config. Pre-call discriminator for routing across creative agents.
supports_refinement	boolean	When true, this creative agent retains produced build_variant leaves (for an agent-defined window) and can re-build from one via refine_from_build_variant_id on build_creative — applying a natural-language instruction in message plus an optional config delta, returning new lineage-linked variants. A build-time capability independent of generation/transformation. When false or absent, refine_from_build_variant_id returns UNSUPPORTED_FEATURE; refine via the transform path (creative_manifest + message) instead.
refinable_retention_seconds	integer	When supports_refinement is true, the guaranteed-minimum window (a floor, not a ceiling) during which a produced build_variant_id stays refinable via refine_from_build_variant_id. A ref within the window SHOULD resolve; the agent MAY retain longer. Omit to leave the window agent-defined (buyers treat refinability as best-effort and handle REFERENCE_NOT_FOUND).
multiplicity	object	Pre-call fan-out discriminators so a buyer knows before sending max_creatives/max_variants: supports_catalog_fanout + max_creatives_limit, supports_variants + max_variants_limit, and variant_dimensions[] (which variant_axis.dimension values are supported). Over-limit requests are clamped to the ceilings (shortfall shown via items_returned < items_total), not rejected. Absent means no fan-out — build_creative produces a single creative. Individual transformers may narrow this via transformer.multiplicity.
supports_spend_controls	boolean	When true, build_creative honors a per-call max_spend ceiling (returns a partial paid build with budget_status: "capped" + a BUDGET_CAP_REACHED advisory rather than overspending) and supports mode: "estimate" dry-runs (a projected cost band, producing/billing nothing). When false or absent, both are rejected with UNSUPPORTED_FEATURE. Meaningful only with bills_through_adcp: true.
bills_through_adcp	boolean	When true, this creative agent bills through the AdCP rate-card surface — list_creatives returns pricing_options (with include_pricing=true and an authenticated account), build_creative populates pricing_option_id and vendor_cost, and report_usage accepts records against the rate card. When false or absent, the agent bills out of band (flat license, SaaS contract, bundled enterprise agreement); buyers should skip pricing fields and tolerate report_usage returning accepted: 0 with BILLING_OUT_OF_BAND errors. Pre-call discriminator for routing across creative agents.

governance

Governance protocol capabilities. Only present if governance is in supported_protocols. Governance agents declare capabilities across four domains: property evaluation, creative evaluation, content standards verification, and policy registry integration.

property_features

Array of property features this governance agent can evaluate. See Property Governance.

Field	Type	Description
feature_id	string	Required. Unique identifier (e.g., mfa_score, coppa_certified). Use registry:{policy_id} prefix for features mapped to Policy Registry entries.
type	string	Required. Data type: binary, quantitative, or categorical
range	object	For quantitative: { min, max }
categories	string[]	For categorical: valid values
description	string	Human-readable description
methodology_url	string	URL to methodology documentation

creative_features

Array of creative features this governance agent can evaluate. Same field schema as property_features. See Creative Governance.

Creative governance agents evaluate creatives for security, content categorization, and regulatory compliance. Buyers filter creatives by feature requirements — for example, blocking creatives flagged for auto_redirect or requiring registry:eu_ai_act_article_50 compliance.

content_standards

Content standards verification capabilities. See Content Standards.

Field	Type	Description
supported	boolean	Whether this agent can serve as a content standards verification agent
calibration_formats	string[]	Artifact asset types this agent can evaluate (e.g., text, image, video, audio)

policy_registry

Policy registry integration capabilities. See Policy Registry.

Field	Type	Description
supported	boolean	Whether this agent consumes policies from the AdCP Policy Registry
domains	string[]	Governance domains this agent covers (e.g., campaign, property, creative, content_standards)

Example governance agent response:

{
  "$schema": "/schemas/protocol/get-adcp-capabilities-response.json",
  "status": "completed",
  "adcp": {
    "major_versions": [3],
    "idempotency": { "supported": true, "replay_ttl_seconds": 86400 }
  },
  "supported_protocols": ["governance"],
  "governance": {
    "property_features": [
      { "feature_id": "mfa_score", "type": "quantitative", "range": { "min": 0, "max": 100 }, "description": "Made For Advertising detection (0=quality content, 100=likely MFA)", "methodology_url": "https://vendor.example.com/methodology/mfa" },
      { "feature_id": "coppa_certified", "type": "binary", "description": "COPPA compliance certification" },
      { "feature_id": "registry:uk_hfss", "type": "binary", "description": "UK HFSS advertising restrictions compliance" },
      { "feature_id": "carbon_score", "type": "quantitative", "range": { "min": 0, "max": 100 }, "description": "Carbon footprint sustainability score", "methodology_url": "https://vendor.example.com/methodology/carbon-score" }
    ],
    "creative_features": [
      { "feature_id": "registry:eu_ai_act_article_50", "type": "binary", "description": "EU AI Act Article 50 — AI-generated content disclosure" },
      { "feature_id": "registry:ca_sb_942", "type": "binary", "description": "California SB 942 — AI transparency compliance" },
      { "feature_id": "auto_redirect", "type": "binary", "description": "Detects auto-redirect behavior in creative code" },
      { "feature_id": "credential_harvest", "type": "binary", "description": "Detects credential harvesting patterns" }
    ],
    "content_standards": {
      "supported": true,
      "calibration_formats": ["text", "image", "video"]
    },
    "policy_registry": {
      "supported": true,
      "domains": ["campaign", "property", "creative", "content_standards"]
    }
  }
}

measurement

Experimental measurement protocol capabilities. Only present if measurement is in supported_protocols; agents implementing it must also list measurement.core in experimental_features. The measurement protocol is currently scoped to get_adcp_capabilities for catalog discovery (this block); additional measurement tasks (reporting, attribution, panel queries) and a baseline compliance storyboard land in subsequent minors. The capability block is shipping now so measurement vendors can publish their per-metric catalogs and AAO can crawl them, before the broader task surface is settled.

Scope. An agent claiming measurement computes one or more quantitative metrics about ad delivery, exposure, or effect (impression verification, viewability, IVT, attention, brand lift, incrementality, outcomes, emissions — vendors define the surface in metrics[]). Returns metric definitions (this block), not pricing or coverage (negotiated per buy via measurement_terms) and not live values (returned per buy via vendor_metric_values). Same mechanical model as compliance_testing and webhook_signing: presence asserts the capability; the block carries the structured payload.

Measurement agents publish a per-metric catalog so buyers know which metrics each vendor offers. This is the canonical source of truth — AAO crawls it to populate the federated measurement-vendor index.

metrics

Array of metrics this measurement agent computes.

Field	Type	Description
metric_id	string	Required. Vendor-scoped identifier (attention_units, gco2e_per_impression, etc.) — matches the metric_id populated in vendor_metric_values on delivery. The full identity is the tuple (vendor.domain, vendor.brand_id, metric_id). Each metric_id MUST be unique within a single agent’s catalog.
standard_reference	string (URI)	Optional URI pointing at the published standard this metric implements (IAB Attention Measurement Guidelines, MRC Viewable Impression Measurement, GARM emissions framework). Distinct from accreditations below — standard_reference is what the metric is built against; accreditations is third-party certification of conformance.
accreditations	object[]	Optional list of third-party accreditations this metric holds (MRC, ARF, JIC bodies, ABC, BARB, AGOF, etc.). Each entry: accrediting_body (required), optional certification_id, valid_until, evidence_url. Buyers asking “is this MRC-accredited?” SHOULD check this array — implementing a standard is not the same as being independently accredited.
unit	string	Unit of the value when reported in vendor_metric_values.value (score, seconds, persons, gCO2e, lift_percent, USD, etc.). Sellers populating vendor_metric_values.unit MUST match this declaration.
description	string	Human-readable description of what the metric measures and any methodology notes. AAO and buyer agents normalize across catalogs from this field plus the structured fields above; classification facets are not declared at the metric level.
methodology_url	string (URI)	URL to vendor’s full methodology documentation. Mirrors governance.property_features[].methodology_url.
methodology_version	string	Optional version identifier (semver, ISO date, or vendor-defined string) for the methodology. When present, buyer agents can pin a contracted version so silent methodology changes are detectable; absence means the vendor does not version their methodology and buyers MUST treat any change as untracked.
ext	object	Vendor extensions per the AdCP ext convention.

Response example

{
  "measurement": {
    "metrics": [
      {
        "metric_id": "attention_units",
        "standard_reference": "https://iabtechlab.com/standards/attention-measurement",
        "accreditations": [
          { "accrediting_body": "MRC", "certification_id": "MRC-ATT-2026-001", "valid_until": "2027-12-31", "evidence_url": "https://mediaratingcouncil.org/accreditations/attentionvendor" }
        ],
        "unit": "score",
        "description": "Eye-tracking-based attention score (0-100). Computed from a panel of 25K opted-in households.",
        "methodology_url": "https://attentionvendor.example/docs/attention-units",
        "methodology_version": "v2.1"
      },
      {
        "metric_id": "engagement_seconds",
        "unit": "seconds",
        "description": "Active dwell time in seconds, measured via in-content telemetry."
      }
    ]
  }
}

Discovery vs. settlement. Buyers MAY hit a measurement agent’s get_adcp_capabilities directly to see its current catalog (live, canonical, no staleness), or query AAO’s federated index for cross-vendor aggregation. The index trades a TTL refresh window for cross-vendor speed; live calls trade speed for currency. Both are valid — typically planning queries hit the index, settlement/audit queries hit the agent.

This is a discovery surface, not a rate card. The catalog tells buyers what a vendor measures and what standards/accreditations back it. Pricing per impression, minimum measurable inventory, attribution windows, geographic coverage, and data-freshness SLAs are negotiated per buy through the seller’s measurement_terms on create_media_buy — not through this catalog.

compliance_testing

Compliance testing capabilities. The presence of this block declares that the agent supports deterministic testing via comply_test_controller. Omit the block if the agent does not support compliance testing.

Production deployments MUST NOT include this block. comply_test_controller is sandbox-only at the deployment level; advertising the capability on a production endpoint is non-conformant even if dispatch is gated. See Compliance test controller § Sandbox gating.

Field	Type	Description
scenarios	string[]	Compliance testing scenarios this agent supports. Values SHOULD include every canonical controller scenario the agent implements, excluding list_scenarios because that value is a discovery operation rather than a test capability. Current canonical values include force_creative_status, force_account_status, force_media_buy_status, force_create_media_buy_arm, force_task_completion, force_session_status, simulate_delivery, simulate_budget_spend, seed_product, seed_pricing_option, seed_creative, seed_plan, seed_media_buy, seed_creative_format, seed_measurement_catalog, query_upstream_traffic, query_provenance_audit_observations, and force_upstream_unavailable. Values MAY also include implementation-specific scenarios. Runners MUST treat scenario names as open strings — new scenarios may be added in additive releases.

Storyboard runners check for the compliance_testing block before running deterministic testing steps. If the agent does not include the block, controller-dependent storyboard steps cannot be validated.

Agents that implement comply_test_controller SHOULD include the compliance_testing capability block and list supported scenarios. Agents that only support a subset of scenarios (e.g., media buy status but not SI sessions) declare only those scenarios — the runner reports unsupported scenario coverage as skipped or partial rather than as a hidden pass.

:::note Compliance testing is sandbox-only at the deployment level — production deployments MUST NOT advertise this block or expose comply_test_controller on any surface. FORBIDDEN is returned only when an in-sandbox caller passes params that reference a non-sandbox account; live-mode probes for the tool by name receive the transport’s standard unknown-tool error. See Sandbox gating. :::

webhook_signing

Declares a seller’s webhook-signing posture. Any seller whose capability surface advertises mutating-webhook emission — including but not limited to media_buy.reporting_delivery_methods containing webhook, media_buy.content_standards.supports_webhook_delivery: true, or wholesale_feed_webhooks.supported: true — MUST include this block with supported: true. A seller that emits no webhooks at all MAY omit the block entirely; the absence of both mutating-webhook emission in other capabilities and this block is an unambiguous “does not emit webhooks” posture. Buyers read the block at onboarding to determine which algorithms to expect per the AdCP webhook-signing profile. Buyers integrating with a seller that advertises mutating-webhook emission while advertising supported: false or omitting this block MUST fail onboarding with a user-actionable error; silent integration with a non-signing-but-webhook-emitting seller is unsafe for any mutating-webhook use case.

Field	Type	Description
supported	boolean	Required when the seller advertises mutating-webhook emission elsewhere in its capability surface. true iff the seller signs outbound webhooks. false means the seller emits webhooks but does not sign them; buyers MUST fail onboarding. Sellers that emit no webhooks SHOULD omit the entire block rather than set supported: false — false is reserved for the unsafe posture of unsigned-webhook emission, not absence-of-webhooks.
profile	string	Required when supported: true. The profile version string. Currently "adcp/webhook-signing/v1". Future versions bump the string.
algorithms	string[]	Required when supported: true. Subset of ["ed25519", "ecdsa-p256-sha256"] — the algorithms this seller will sign webhooks with. Matches the webhook-signing verifier allowlist (see Verifier checklist for webhooks, step 4). Buyers MUST be prepared to verify any algorithm listed AND MUST reject onboarding with a user-actionable error if an advertised algorithm is outside this enumerated set — a seller advertising an out-of-set algorithm (e.g., hs256) is either misconfigured or signalling a non-conforming profile.
legacy_hmac_fallback	boolean	Required when supported: true. true iff the seller supports the legacy HMAC-SHA256 scheme when the buyer populates push_notification_config.authentication.credentials or accounts[].notification_configs[].authentication.credentials. false is the recommended posture in 3.x — the HMAC scheme is removed in AdCP 4.0.

Example:

{
  "webhook_signing": {
    "supported": true,
    "profile": "adcp/webhook-signing/v1",
    "algorithms": ["ed25519", "ecdsa-p256-sha256"],
    "legacy_hmac_fallback": false
  }
}

The webhook-signing block is parallel to request_signing (inbound) and the two blocks cover the two signing directions between buyer and seller. Buyers SHOULD validate both at onboarding; a seller that signs one direction but not the other has a lopsided security posture that operators need to notice explicitly.

extensions_supported

Array of extension namespaces this agent supports. Buyers can expect meaningful data in ext.{namespace} fields on responses from this agent.

Field	Type	Description
extensions_supported	string[]	Extension namespaces (e.g., ["iab_tcf", "iab_gpp"])

Extension schemas are published in the AdCP extension registry. When an agent declares support for an extension, buyers know to look for and process ext.{namespace} data in responses.

Example:

{
  "extensions_supported": ["iab_tcf", "iab_gpp", "acmecorp"]
}

This tells buyers:

• Responses may include ext.iab_tcf with IAB TCF consent data
• Responses may include ext.iab_gpp with IAB GPP (Global Privacy Platform) signals
• Responses may include ext.acmecorp with vendor-specific data from Acme Corp

experimental_features

Array of experimental AdCP surfaces this agent implements. A surface is experimental when its schema carries x-status: experimental — it is part of the core protocol but not yet frozen and may break between 3.x releases with 6 weeks’ notice. Sellers that implement any experimental surface MUST list its feature id here.

Field	Type	Description
experimental_features	string[]	Experimental feature ids (e.g., ["brand.rights_lifecycle", "governance.campaign", "measurement.core", "trusted_match.core", "sponsored_intelligence.core"])

Buyers should inspect experimental_features before relying on an experimental surface. A seller that does not list a surface is asserting it does not implement it — there is no “silently experimental” mode.

Example:

{
  "experimental_features": ["brand.rights_lifecycle", "measurement.core", "trusted_match.core"]
}

See experimental status for the full stability contract, graduation criteria, and client guidance.

wholesale_feed_versioning

Conditional-fetch token capabilities for get_products and get_signals. Independent of wholesale feed webhooks: an agent MAY support cheap version probes without pushing change payloads, and an agent MAY push change payloads while still requiring reconciliation reads for repair.

Field	Type	Description
supported	boolean	Required. Whether the agent returns wholesale_feed_version on responses and honors if_wholesale_feed_version on requests. When absent or false, buyers can still probe by reading the response (the field-presence detection path) but can’t pre-flight-decide which agents to cache versions for.
pricing_version_separate	boolean	Whether the agent tracks pricing_version independently of wholesale_feed_version. When true, callers can send if_pricing_version alongside if_wholesale_feed_version for finer-grained “did prices change?” probes. When false or absent, the agent collapses both into wholesale_feed_version — sending if_pricing_version is wasted bytes.
cache_scope_account	boolean	Whether the agent ever returns cache_scope: "account" (i.e., publishes per-account overlays distinct from the public rate card). When true, buyers MUST be prepared to maintain account-overlay caches alongside the public layer. When false or absent, all responses are cache_scope: "public" — the agent’s rate card is universal across accounts. Note: declaring true advertises that the agent runs custom-pricing deals, which is itself a small market-posture signal; agents preferring confidentiality MAY omit the field and detect-on-call instead.

Example:

{
  "wholesale_feed_versioning": {
    "supported": true,
    "pricing_version_separate": true,
    "cache_scope_account": true
  }
}

wholesale_feed_webhooks

Per-agent wholesale product-feed and wholesale signals-feed webhook capabilities. Declared by sales agents (products) and signals agents (signals). When supported is true, consumers can register sync_accounts.accounts[].notification_configs[] entries for product.*, signal.*, and wholesale_feed.bulk_change events and receive the actual change payload in each webhook. See specs/wholesale-feed-webhooks.md for the full spec.

Terminology. Here “wholesale feed” means the agent’s buyable wholesale product feed and wholesale signals feed exposed by get_products and get_signals. It is distinct from sync_catalogs, which pushes buyer-provided campaign input feeds into a seller account for campaign execution.

Complementary to (and independent of) wholesale_feed_versioning: webhooks push changed products/signals or bulk-change summaries; version tokens give a cheap repair and reconciliation probe. Adopters MAY ship either, both, or neither.

Agents that declare supported: true MUST apply the same account/caller authorization and scope predicate used by the corresponding wholesale read before emitting each webhook. A caller that could not see a product, signal, price, or account overlay through get_products buying_mode: "wholesale" or get_signals discovery_mode: "wholesale" MUST NOT receive a webhook revealing that change. Agents unable to guarantee per-principal filtering MUST NOT declare support.

Capability consistency. Agents listing any product.* value in event_types[] MUST declare and support wholesale get_products (media_buy.buying_modes includes "wholesale"). Agents listing any signal.* value MUST declare and support wholesale get_signals (signals.discovery_modes includes "wholesale"). Agents listing wholesale_feed.bulk_change MUST have at least one of those wholesale repair paths, and each bulk-change payload’s affected_entity_type MUST name only a feed family the agent can repair through a declared wholesale read.

Consumer precedence. When more than one mechanism is declared, consumers SHOULD prefer them in this order: (1) wholesale_feed_webhooks when maintaining a long-lived mirror (lowest latency, lowest seller cost); (2) wholesale_feed_versioning conditional fetch for occasional polling and webhook repair; (3) wholesale enumeration via buying_modes / discovery_modes for cold start, wholesale_feed.bulk_change, or any missed/distrusted push.

Field	Type	Description
supported	boolean	Required. Whether this agent can push wholesale feed change payloads through account-level sync_accounts.accounts[].notification_configs[]. When false or this stanza is absent, consumers fall back to wholesale polling, optionally with if_wholesale_feed_version probes.
event_types	string[]	Event types this agent can emit. Sales agents emit product.* events; signals agents emit signal.* events; agents that are both can emit both event families. product.* requires wholesale get_products; signal.* requires wholesale get_signals; wholesale_feed.bulk_change requires at least one declared wholesale repair path and names one affected feed the consumer repairs by re-reading via get_products or get_signals.

Example (sales + signals agent):

{
  "wholesale_feed_webhooks": {
    "supported": true,
    "event_types": [
      "product.created", "product.updated", "product.priced", "product.removed",
      "signal.created", "signal.updated", "signal.priced", "signal.removed",
      "wholesale_feed.bulk_change"
    ]
  }
}

The Capability Contract

If a capability is declared, the seller MUST honor it.

• media_buy.execution.targeting.geo_postal_areas.US contains zip → Buyer can send { country: "US", system: "zip", values: [...] }, seller MUST honor it
• media_buy.execution.targeting.geo_postal_areas.us_zip: true → Buyer can send the deprecated { system: "us_zip", values: [...] } form, and SDKs can backfill the native { country: "US", system: "zip", values: [...] } form
• media_buy.execution.targeting.geo_postal_areas.ZA contains postal_code → Buyer can send normal South African postal codes, seller MUST honor them
• media_buy.execution.targeting.geo_metros.nielsen_dma: true → Buyer can send DMA codes, seller MUST honor them
• media_buy.content_standards object present → Seller MUST apply content standards when provided
• media_buy.audience_targeting object present → Seller MUST support sync_audiences and audience targeting overlays
• media_buy.conversion_tracking object present → Seller MUST support sync_event_sources and log_event
• AXE URL in media_buy.execution.axe_integrations → Seller can execute through that exchange (legacy — new integrations use TMP)

No silent ignoring. If a seller can’t support a capability, they should declare false or omit it.

Common Scenarios

Basic Capability Discovery

import { AdcpClient } from '@adcp/sdk';

const client = new AdcpClient({ baseUrl: 'https://seller.example.com/mcp' });

// Get seller capabilities
const result = await client.getAdcpCapabilities({});

if (result.errors) {
  throw new Error(`Request failed: ${result.errors[0].message}`);
}

// Check protocol support
console.log(`AdCP versions: ${result.adcp.major_versions.join(', ')}`);
console.log(`Supported protocols: ${result.supported_protocols.join(', ')}`);

// Check media-buy capabilities
if (result.supported_protocols.includes('media_buy')) {
  const mediaBuy = result.media_buy;

  // Check content standards support (object presence = signal)
  if (mediaBuy.content_standards) {
    console.log('Content standards supported');
  }

  // Check AXE integrations (legacy — new integrations use TMP via trusted_match on products)
  if (mediaBuy.execution?.axe_integrations?.includes('https://axe.example.com')) {
    console.log('AXE integration available');
  }

  // Check geo targeting (normalize native country keys and deprecated aliases)
  const postalSupport = mediaBuy.execution?.targeting?.geo_postal_areas;
  if (postalSupport?.US?.includes('zip') || postalSupport?.us_zip === true) {
    console.log('US ZIP code targeting supported');
  }

  // Portfolio overview
  console.log(`Publishers: ${mediaBuy.portfolio.publisher_domains.length}`);
  console.log(`Channels: ${mediaBuy.portfolio.primary_channels?.join(', ')}`);
}

Check multi-protocol support

const caps = await client.getAdcpCapabilities({});

const sellsMedia = caps.supported_protocols.includes('media_buy');
const managesCreatives = caps.supported_protocols.includes('creative');

if (sellsMedia && managesCreatives) {
  // Single agent handles both protocols — no need to discover a separate service
  const formats = await client.listCreativeFormats({});
  const delivery = await client.getCreativeDelivery({
    media_buy_ids: ['mb_12345']
  });
}

Filter sellers by capability

// Find sellers that support specific requirements
async function findCompatibleSellers(sellers, requirements) {
  const compatible = [];

  for (const sellerUrl of sellers) {
    const client = new AdcpClient({ baseUrl: sellerUrl });
    const caps = await client.getAdcpCapabilities({});

    if (caps.errors) continue;

    // Must support media_buy protocol
    if (!caps.supported_protocols.includes('media_buy')) continue;

    const mediaBuy = caps.media_buy;

    // Check AXE integration requirement (legacy — new integrations use TMP)
    if (requirements.axeIntegration) {
      if (!mediaBuy.execution?.axe_integrations?.includes(requirements.axeIntegration)) {
        continue;
      }
    }

    // Check geo targeting requirement
    if (requirements.postalCodeTargeting) {
      const postalSupport = mediaBuy.execution?.targeting?.geo_postal_areas;
      if (!(postalSupport?.US?.includes('zip') || postalSupport?.us_zip === true)) {
        continue;
      }
    }

    // Check content standards requirement (object presence = signal)
    if (requirements.contentStandards) {
      if (!mediaBuy.content_standards) {
        continue;
      }
    }

    compatible.push({ url: sellerUrl, capabilities: caps });
  }

  return compatible;
}

// Usage
const sellers = await findCompatibleSellers(
  ['https://seller1.com/mcp', 'https://seller2.com/mcp'],
  {
    axeIntegration: 'https://axe.example.com',
    postalCodeTargeting: true,
    contentStandards: true
  }
);

Use Capabilities to Build Targeting

Capabilities tell you what you CAN specify in create_media_buy targeting. Use required_geo_targeting to filter products to sellers that support specific geo targeting levels and systems:

// First, check capabilities
const caps = await client.getAdcpCapabilities({});

if (!caps.supported_protocols.includes('media_buy')) {
  throw new Error('Seller does not support media_buy protocol');
}

const mediaBuy = caps.media_buy;
const postalSupport = mediaBuy.execution?.targeting?.geo_postal_areas;

// Filter products to sellers with specific geo targeting capabilities
const products = await client.getProducts({
  brief: "Premium video inventory in US for ZIP-targeted campaign",
  filters: {
    channels: ['olv', 'ctv'],
    countries: ['US'],
    // Require seller supports ZIP targeting (capability filter - no actual ZIPs needed)
    // level = granularity, system = classification taxonomy
    required_geo_targeting: [
      { level: 'postal_area', country: 'US', system: 'zip' }
    ],
    // Only include if seller supports this AXE (legacy — new integrations use TMP)
    required_axe_integrations: ['https://axe.example.com']
  }
});

// Then, create media buy with fine-grained targeting
// (if seller supports postal areas, we can target specific ZIP codes)
const buy = await client.createMediaBuy({
  brand: { domain: 'mybrand.com' },
  packages: [{
    product_id: products.products[0].product_id,
    pricing_option_id: products.products[0].pricing_options[0].id,
    budget: 10000,
    // Targeting overlay refines delivery within product coverage
    targeting_overlay: {
      geo_countries: ['US'],
      // Only specify ZIP targeting if seller supports it
      ...((postalSupport?.US?.includes('zip') || postalSupport?.us_zip === true) && {
        geo_postal_areas: [{
          country: 'US',
          system: 'zip',
          values: ['10001', '10002', '10003', '10004', '10005']
        }]
      })
    }
  }],
  start_time: { type: 'asap' },
  end_time: '2025-03-01T00:00:00Z'
});

Two models for product geography:

Inventory Type	Filter By	Example
Digital (display, OLV, CTV)	Capability: required_geo_targeting	Products have broad coverage, target at buy time
Local (radio, DOOH, local TV)	Coverage: metros, regions	Products ARE geographically bound

• Digital inventory: Use countries + required_geo_targeting (capability), apply fine-grained targeting in create_media_buy
• Local inventory: Use metros/regions (coverage) to find products with coverage in your target markets

Local Inventory Example (Radio, DOOH)

For locally-bound inventory, products ARE geographically specific. A radio station in NYC DMA only covers NYC.

// Find radio products in specific DMAs
const radioProducts = await client.getProducts({
  brief: "Radio inventory in NYC and LA markets",
  filters: {
    channels: ['radio'],
    // Coverage filter: products must cover these metros
    metros: [
      { system: 'nielsen_dma', code: '501' },  // NYC
      { system: 'nielsen_dma', code: '803' }   // LA
    ]
  }
});

// For local inventory, targeting_overlay is optional -
// the product's coverage IS the geography
const buy = await client.createMediaBuy({
  brand: { domain: 'mybrand.com' },
  packages: [{
    product_id: radioProducts.products[0].product_id,
    pricing_option_id: radioProducts.products[0].pricing_options[0].id,
    budget: 5000
    // No targeting_overlay needed - product covers NYC DMA
  }],
  start_time: { type: 'asap' },
  end_time: '2025-03-01T00:00:00Z'
});

Response Example

{
  "$schema": "/schemas/protocol/get-adcp-capabilities-response.json",
  "status": "completed",
  "adcp": {
    "major_versions": [3],
    "idempotency": { "supported": true, "replay_ttl_seconds": 86400 }
  },
  "supported_protocols": ["media_buy"],
  "account": {
    "require_operator_auth": false,
    "supported_billing": ["operator", "agent"]
  },
  "media_buy": {
    "creative_approval_mode": "auto_approve",
    "features": {
      "inline_creative_management": true,
      "property_list_filtering": true
    },
    "execution": {
      "axe_integrations": ["https://axe.example.com"],
      "creative_specs": {
        "vast_versions": ["4.0", "4.1", "4.2"],
        "mraid_versions": ["3.0"],
        "vpaid": false,
        "simid": true
      },
      "targeting": {
        "geo_countries": true,
        "geo_regions": true,
        "geo_metros": {
          "nielsen_dma": true
        },
        "geo_postal_areas": {
          "us_zip": true,
          "us_zip_plus_four": true,
          "US": ["zip", "zip_plus_four"],
          "GB": ["outward", "full"],
          "CA": ["fsa", "full"],
          "ZA": ["postal_code"]
        },
        "language": true,
        "keyword_targets": {
          "supported_match_types": ["broad", "phrase", "exact"]
        },
        "negative_keywords": {
          "supported_match_types": ["broad", "exact"]
        }
      }
    },
    "content_standards": {
      "supports_local_evaluation": true,
      "supported_channels": ["display", "olv"],
      "supports_webhook_delivery": false
    },
    "audience_targeting": {
      "supported_identifier_types": ["hashed_email", "hashed_phone"],
      "supports_platform_customer_id": false,
      "supported_uid_types": ["uid2", "rampid"],
      "minimum_audience_size": 500,
      "matching_latency_hours": { "min": 1, "max": 24 }
    },
    "conversion_tracking": {
      "multi_source_event_dedup": false,
      "supported_event_types": ["purchase", "lead", "add_to_cart", "view_content"],
      "supported_action_sources": ["website", "app"],
      "attribution_windows": [
        { "post_click": [{ "interval": 7, "unit": "days" }, { "interval": 28, "unit": "days" }], "post_view": [{ "interval": 1, "unit": "days" }, { "interval": 7, "unit": "days" }] }
      ]
    },
    "portfolio": {
      "publisher_domains": ["example.com", "news.example.com"],
      "primary_channels": ["display", "olv"],
      "primary_countries": ["US", "CA"]
    }
  },
  "extensions_supported": ["acmecorp"],
  "last_updated": "2025-01-23T10:00:00Z"
}

This tells buyers:

• AdCP versions: Version 1
• Protocols: Media buy only
• Auth model: Agent-trusted (require_operator_auth: false) — authenticate once, declare brands via sync_accounts
• Billing: Operator or agent billing; default is operator
• Country targeting: Available (ISO 3166-1 alpha-2: US, GB, etc.)
• Region targeting: Available (ISO 3166-2: US-NY, GB-SCT, etc.)
• Metro targeting: Nielsen DMA only (US market)
• Postal targeting: US ZIP, UK outward codes, Canadian FSA
• Audience targeting: Accepts hashed email, hashed phone, UID2, and RampID; minimum matched audience size of 500; matching latency 1–24 hours
• Conversion tracking: Accepts purchase, lead, add_to_cart, view_content events from website/app; no multi-source dedup
• Extensions: Vendor-specific data in ext.acmecorp

Multi-protocol agent

An agent can implement multiple protocols from a single endpoint. This is common for sellers that manage both media buying and creative generation — the buyer calls all tasks on the same URL.

{
  "$schema": "/schemas/protocol/get-adcp-capabilities-response.json",
  "status": "completed",
  "adcp": {
    "major_versions": [3],
    "idempotency": { "supported": true, "replay_ttl_seconds": 86400 }
  },
  "supported_protocols": ["media_buy", "creative"],
  "account": {
    "require_operator_auth": false,
    "supported_billing": ["operator"]
  },
  "media_buy": {
    "creative_approval_mode": "require_human",
    "features": {
      "inline_creative_management": true
    },
    "portfolio": {
      "publisher_domains": ["news.example.com"],
      "primary_channels": ["display", "olv"]
    }
  },
  "creative": {
    "has_creative_library": true,
    "supports_generation": true,
    "supports_transformation": false,
    "supports_compliance": false,
    "bills_through_adcp": true
  }
}

This agent supports:

• Media Buy Protocol: Product discovery, media buying, delivery reporting
• Creative Protocol: Creative library management, AI-powered creative generation, variant-level delivery analytics via get_creative_delivery
• Shared account: A single account established via sync_accounts applies to both protocols

When supported_protocols includes "creative", the buyer can call Creative Protocol tasks (list_creative_formats, sync_creatives, get_creative_delivery, etc.) on this agent. See Creative capabilities on sales agents.

Geo Standards Reference

Level	System	Examples
Country	ISO 3166-1 alpha-2	US, GB, DE, CA
Region	ISO 3166-2	US-NY, GB-SCT, DE-BY, CA-ON
Metro (US)	nielsen_dma	501 (NYC), 803 (LA), 602 (Chicago)
Metro (UK)	uk_itl2	UKI (London), UKD (North West)
Metro (EU)	eurostat_nuts2	DE30 (Berlin), FR10 (Île-de-France)
Postal (US)	US / zip	10001, 90210
Postal (US)	US / zip_plus_four	10001-1234
Postal (UK)	GB / outward	SW1, EC1, M1
Postal (UK)	GB / full	SW1A 1AA
Postal (CA)	CA / fsa	K1A, M5V

Migration from list_authorized_properties (v2)

The list_authorized_properties task was removed in v3. If migrating from v2:

Old Field	New Location
publisher_domains	media_buy.portfolio.publisher_domains
primary_channels	media_buy.portfolio.primary_channels
primary_countries	media_buy.portfolio.primary_countries
portfolio_description	media_buy.portfolio.description
advertising_policies	media_buy.portfolio.advertising_policies
last_updated	last_updated (top level)

New fields:

• adcp.major_versions - Version compatibility
• supported_protocols - Which domain protocols are supported
• media_buy.features - Optional feature support
• media_buy.execution.axe_integrations - Ad exchange support
• media_buy.execution.creative_specs - VAST/MRAID versions
• media_buy.execution.targeting - Geo targeting granularity

Error Handling

Error Code	Description	Resolution
AUTH_MISSING	No credentials presented	Provide credentials via auth header
AUTH_INVALID	Credentials rejected (expired / revoked)	Human credential rotation required
VERSION_UNSUPPORTED	Declared adcp_major_version not in seller’s major_versions	Call without adcp_major_version to discover supported versions, then retry
INTERNAL_ERROR	Server error	Retry with backoff

Best Practices

1. Cache Capabilities Capabilities rarely change. Cache results and use last_updated for staleness detection.

2. Check Protocol Support First Before accessing protocol-specific fields, verify the protocol is in supported_protocols.

3. Check Before Requesting Don’t send postal areas for a system the seller doesn’t support. Don’t request features the seller doesn’t support.

4. Fail Fast on Incompatibility If a seller doesn’t support required capabilities, skip them early rather than discovering failures later.

5. Read the Auth Model Before Proceeding Check account.require_operator_auth immediately after discovery. Agent-trusted and operator-scoped flows diverge significantly: the former uses a single credential for all brands and operators, the latter requires per-operator credentials and sessions.

6. Use Protocol Version for Routing Route requests to appropriate API versions based on adcp.major_versions.

Next Steps

After discovering capabilities:

1. Set up accounts: Follow the auth model from account.require_operator_auth — see Accounts and Agents
2. Filter products: Use get_products with capability-aware filters
3. Validate properties: Fetch publisher adagents.json files for property definitions
4. Create buys: Use create_media_buy with supported features

Learn More

• Accounts and Agents - Auth models, account setup, billing
• adagents.json Specification - Publisher authorization files
• Product Filters - Capability-aware filtering
• Content Standards - Brand safety configuration