# AdCP - Ad Context Protocol: 3.1 Protocol > AdCP (Ad Context Protocol) is the open standard for agentic advertising. It defines how AI agents buy media, generate creatives, activate audiences, and enforce governance across platforms. Current stable documentation index: https://docs.adcontextprotocol.org/llms-current.md. ## Protocol ### Media Buy - [Media buy protocol](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/index.md): AdCP media buy protocol walkthrough — follow a campaign from brief to delivery across CTV, display, and audio using one unified workflow. - [Commerce Media](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/commerce-media.md): Commerce media in AdCP: why retail media networks should stand up agentic storefronts instead of building self-service platforms, and how to model sponsored products, in-store digital, and closed-loop attribution. #### Concepts - [Product Discovery](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/product-discovery/index.md): AdCP product discovery — use natural language campaign briefs to find advertising inventory across publishers. Covers brief writing, product structures, and refinement. - [Brief Expectations](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/product-discovery/brief-expectations.md): AdCP brief expectations — how to write campaign briefs for get_products. Required fields, optional details, and implementation guidance for publishers and buyer agents. - [Example Campaign Briefs](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/product-discovery/example-briefs.md): AdCP example campaign briefs — annotated examples from minimal to advanced showing how natural language briefs drive product discovery in get_products. - [Media Products](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/product-discovery/media-products.md): AdCP media products — the core sellable unit in the protocol. Covers product structure, pricing options, delivery types, format references, and catalog-driven inventory. - [Collections and installments](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/product-discovery/collections-and-installments.md): AdCP collections and installments — model podcast, CTV, and streaming content as dimensions on media products. Enables collection-level targeting and installment-specific ad placement. - [Refinement](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/product-discovery/refinement.md): AdCP product refinement — iterate on discovered products and proposals using refine mode in get_products. Adjust selections and request changes before creating a media buy. - [Media Buy Lifecycle](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/media-buys/index.md): AdCP media buy lifecycle — create, update, monitor, and optimize campaigns across sellers using create_media_buy, update_media_buy, and get_media_buys tasks. - [Media Buy Lifecycle Flow](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/media-buys/lifecycle.md): Step-by-step sequence from product discovery through delivery, including the guaranteed-deal IO acceptance path and creative sync timing. - [Optimization & Reporting](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/media-buys/optimization-reporting.md): AdCP optimization and reporting — monitor delivery metrics, analyze dimensional breakdowns, share performance feedback, and optimize active media buys. - [Policy Compliance](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/media-buys/policy-compliance.md): AdCP policy compliance — how publishers enforce brand safety and regulatory checks during product discovery and media buy creation. Includes policy types and violation handling. - [Creative Lifecycle](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/creatives/index.md): AdCP creative lifecycle — discover supported formats, sync creative assets to sellers, manage libraries, and track approval status across campaigns. - [Conversion Tracking & Optimization Goals](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/conversion-tracking/index.md): AdCP conversion tracking — configure pixels and event sources with sync_event_sources, send conversion events with log_event, and set optimization goals for campaign delivery. - [Pricing Models](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/advanced-topics/pricing-models.md): AdCP pricing models — CPM, CPCV, CPP, CPC, CPA, time-based, and DOOH pricing. Publisher-declared, buyer-selected model with rate card support. - [Targeting](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/advanced-topics/targeting.md): AdCP targeting — how natural language briefs replace taxonomy-based audience selection, with geographic overlays and real-time decisioning at impression time. - [Accountability](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/advanced-topics/accountability.md): How buyers and sellers negotiate, enforce, and resolve performance standards, measurement terms, and cancellation policies in AdCP guaranteed buys. - [Billing Authority](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/advanced-topics/billing-authority.md): How AdCP names the authoritative counter of a media buy's billing metric, marks numbers as final, and reconciles between buyer and seller views when those views disagree. #### Building - [Capability Discovery](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/capability-discovery/index.md): AdCP capability discovery — understand what creative formats a seller supports and which properties they represent before buying media. - [Implementing Standard Format Support](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/capability-discovery/implementing-standard-formats.md): Implementing standard creative formats in AdCP — reference IAB formats from the AdCP creative reference agent instead of redefining display, video, and native specs. - [Agentic eXecution Engine (AXE)](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/advanced-topics/agentic-execution-engine.md): Agentic eXecution Engine (AXE) — AdCP's real-time execution layer for brand suitability enforcement, frequency capping, and dynamic audience targeting at impression time. - [Accounts & Security](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/advanced-topics/accounts-and-security.md): AdCP accounts and security — authentication, rate cards, billing entities, and data isolation for multi-tenant media buying between buyer and seller agents. - [Sandbox mode](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/advanced-topics/sandbox.md): AdCP sandbox mode — test product discovery, campaign creation, creatives, and delivery with simulated data. No real spend or production side effects. #### Reference - [Media Buy Specification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/specification.md): AdCP media buy specification — transport layer, task definitions, JSON schemas, authentication, and compliance requirements for agent-to-agent advertising. - [Task Reference](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/index.md): AdCP media buy task reference — all tasks for product discovery, campaign creation, delivery reporting, creatives, audiences, and conversion tracking with schemas and examples. - [get_products](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/get_products.md): get_products task — discover advertising inventory in AdCP using natural language campaign briefs or structured filters. Returns matched products with pricing and formats. - [create_media_buy](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/create_media_buy.md): create_media_buy task — create advertising campaigns in AdCP from discovered products. Handles packages, budgets, flight dates, governance rules, and approval workflows. - [sync_catalogs](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/sync_catalogs.md): sync_catalogs task — sync product feeds, store locations, and vertical catalogs (hotel, flight, vehicle, real estate) to AdCP seller accounts for catalog-driven campaigns. - [get_media_buys](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/get_media_buys.md): get_media_buys task — retrieve media buy status in AdCP including creative approvals, missing assets, configuration, and optional near-real-time delivery snapshots. - [get_media_buy_delivery](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/get_media_buy_delivery.md): get_media_buy_delivery task — retrieve impressions, spend, pacing, and dimensional breakdowns for active AdCP campaigns. Supports custom date ranges and metric filtering. - [update_media_buy](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/update_media_buy.md): update_media_buy task — modify active AdCP campaigns with PATCH semantics. Update budgets, flight dates, targeting, status, and package-level settings. - [provide_performance_feedback](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/provide_performance_feedback.md): provide_performance_feedback task — share normalized performance scores with AdCP publishers so sellers can optimize delivery based on buyer-observed outcomes. - [sync_event_sources](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/sync_event_sources.md): sync_event_sources task — configure website pixels, mobile SDKs, server-to-server integrations, and seller- or platform-native event sources on AdCP seller accounts for conversion tracking and attribution. - [log_event](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/log_event.md): log_event task — send conversion and marketing events to AdCP sellers in batches. Supports attribution, campaign optimization, ROAS measurement, and test events. - [sync_audiences](https://docs.adcontextprotocol.org/dist/docs/3.1.24/media-buy/task-reference/sync_audiences.md): sync_audiences task — upload hashed first-party CRM audiences to AdCP seller accounts for retargeting, suppression, and lookalike expansion. Supports match status tracking. ### Creative - [Creative protocol](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/index.md): The AdCP Creative Protocol manages ad creative from brief to delivery across CTV, display, and social using AI agents and standardized formats. #### Concepts - [Key concepts](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/key-concepts.md): Assets, formats, manifests, and creative agents are the four building blocks of the AdCP Creative Protocol for programmatic ad creative. - [AI creative for campaign teams](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/ai-creative-overview.md): AI creative in AdCP lets campaign teams write a brief and get production-ready ads generated across formats without learning the protocol. - [Generative Creative](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/generative-creative.md): Generative creative in AdCP uses AI to produce ad assets from a brief with three tiers: static manifests, asset group optimization, and per-context generation. - [Creative libraries and concepts](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/creative-libraries.md): Creative libraries in AdCP let buyers browse, organize, and track approval status for creatives across ad servers and management platforms. - [Catalogs](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/catalogs.md): Catalogs in AdCP are typed data feeds that supply items for ad rendering across platforms. - [Catalog item schemas](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/catalog-schemas.md): AdCP catalog item schemas define required fields and structures for job, hotel, vehicle, flight, real estate, and other vertical data feeds. #### Building Creative Agents - [Implementing Creative Agents](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/implementing-creative-agents.md): How to build an AdCP creative agent that defines formats, validates manifests, generates previews, and hosts a creative library. - [Creative capabilities on sales agents](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/sales-agent-creative-capabilities.md): Sales agents in AdCP implement the Creative Protocol alongside Media Buy for inline creative management and generative ad formats. - [Multi-agent creative orchestration](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/multi-agent-orchestration.md): Multi-agent creative orchestration in AdCP routes requests across agents, distributes assets to sellers, and aggregates delivery data. - [Creative Manifests](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/creative-manifests.md): Creative manifests in AdCP are reusable presets that supply concrete asset values to satisfy format requirements for programmatic ad delivery. - [Private assets](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/private-assets.md): Private assets in AdCP use presigned URLs to grant temporary access to files stored in DAMs, S3 buckets, or authenticated sources. #### Formats and Assets - [Creative Formats](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/formats.md): Creative formats in AdCP define asset requirements, technical constraints, and rendering behavior that shape how ads are built and delivered. - [Asset Types](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/asset-types.md): AdCP asset types define standardized properties for images, video, text, audio, tags, and tracking URLs used in creative formats. - [Template Format IDs](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/template-format-ids.md): Template format IDs in AdCP let a single format definition support many dimension variants without creating separate formats for each size. - [Universal Macros](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/universal-macros.md): Universal macros in AdCP insert dynamic tracking data into creatives with platform-agnostic placeholders replaced at impression time. #### Channel Guides - [Video Ads](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/channels/video.md): Video ad formats in AdCP cover hosted files, VAST tags, inline XML, and multi-resolution encoding for pre-roll, mid-roll, and post-roll ads. - [CTV and connected TV](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/channels/ctv.md): CTV ad formats in AdCP define SSAI and CSAI delivery, companion ads, interactive overlays, and encoding requirements for connected TV. - [Broadcast TV](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/channels/broadcast.md): Broadcast TV ad formats in AdCP define spot file delivery, creative identifier integration, and measurement maturation windows for linear television. - [Display Ads](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/channels/display.md): Display ad formats in AdCP specify static banners, HTML5 creatives, third-party tags, and responsive IAB standard sizes for programmatic ads. - [Audio Ads](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/channels/audio.md): Audio ad formats in AdCP cover streaming audio, podcast dynamic ad insertion, VAST/DAAST tags, and companion banner specifications. - [DOOH (Digital Out-of-Home)](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/channels/dooh.md): DOOH ad formats in AdCP define digital billboard, transit screen, and venue display specifications with venue-based impression tracking. - [Carousel & Multi-Asset Formats](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/channels/carousels.md): Carousel and multi-asset ad formats in AdCP use repeatable asset groups for product carousels, image slideshows, and story sequences. - [Social and feed-native](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/channels/social-native.md): Social and feed-native ad formats in AdCP define buyer-provided assets that platforms wrap in their own UI as promoted posts and sponsored content. #### Compliance - [Accessibility](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/accessibility.md): AdCP accessibility support lets formats declare WCAG conformance levels and requires accessible assets like alt text and captions. - [AI provenance and disclosure](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/provenance.md): AdCP provenance metadata declares AI involvement, tools used, and regulatory disclosure obligations on creative assets and manifests. #### Reference - [Creative Specification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/specification.md): The AdCP Creative Protocol specification defines format discovery, manifest validation, AI creative generation, and preview rendering. - [build_creative](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/task-reference/build_creative.md): build_creative generates, transforms, or retrieves ad creative manifests in AdCP from a natural language brief to production-ready assets. - [preview_creative](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/task-reference/preview_creative.md): preview_creative renders an existing creative manifest into viewable output in AdCP, in single or batch mode, returning URL, image, or HTML output. - [preview_creative (Advanced)](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/task-reference/preview_creative-advanced.md): Advanced AdCP preview patterns including format showcase pages, caching strategies, and batch preview workflows for creative agents. - [list_creative_formats](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/task-reference/list_creative_formats.md): list_creative_formats discovers available ad format specifications from any AdCP agent, including asset requirements and technical constraints. - [list_creatives](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/task-reference/list_creatives.md): list_creatives browses and filters creatives in an AdCP library by format, status, concept, and tags with cursor-based pagination. - [sync_creatives](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/task-reference/sync_creatives.md): sync_creatives uploads and manages creative assets in an AdCP library with bulk uploads, upsert semantics, and generative creative support. - [get_creative_delivery](https://docs.adcontextprotocol.org/dist/docs/3.1.24/creative/task-reference/get_creative_delivery.md): get_creative_delivery retrieves variant-level delivery data with manifests and performance metrics for generative and static creatives in AdCP. ### Governance - [Governance protocol](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/overview.md): AdCP governance ensures human oversight of autonomous AI advertising through three-party validation, budget controls, and brand safety enforcement. - [RFC process](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/rfc-process.md): How to propose and ratify material changes to AdCP — the lifecycle from draft to specification change, including proposal template and decision-record format. - [Embedded human judgment](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/embedded-human-judgment.md): Embedded Human Judgment (EHJ) is a set of principles and an oversight framework for keeping humans accountable when AI agents allocate capital, shape information environments, and execute advertising decisions at scale. - [Policy Registry](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/policy-registry.md): The AdCP Policy Registry is a shared library of machine-readable compliance policies that governance agents reference by ID during campaign validation. - [Policy Registry: Sync and versioning](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/policy-registry-sync.md): Operational pattern for keeping campaign plans synchronized with the AdCP Policy Registry — version pinning, registry version bumps, effective_date adoption, sunset behavior, and the additive-only invariant on inline policies. - [Policy Attribution](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/policy-attribution.md): How producers tag mechanism-level filters and measurements with the authorizing policy, so audit trails and governance findings can trace back to why a specific threshold or evaluation exists. - [Annex III & Article 22 obligations](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/annex-iii-obligations.md): How AdCP's policy framework supports deployer obligations under GDPR Article 22 and EU AI Act Annex III for regulated verticals — credit, insurance, employment, housing. - [Working group charter](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/working-group-charter.md): Operational charter for the AdCP Working Group: quorum, voting thresholds, cadence, recusal, and escalation. #### Property Governance - [Property Governance](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/property/index.md): AdCP Property Governance standardizes identification, authorization, enrichment, and selection of advertising properties across all media channels. - [adagents.json Tech Spec](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/property/adagents.md): adagents.json is the publisher-hosted file in AdCP that declares advertising properties and authorizes sales agents to sell inventory. - [Managed Network Deployment](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/property/managed-networks.md): How managed publisher networks deploy adagents.json across thousands of domains using the URL reference pattern, delegation types, and common infrastructure approaches. - [Understanding Authorization](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/property/authorized-properties.md): Authorized properties in AdCP let buyers restrict campaigns to verified inventory using property lists and supply path validation. - [Property Governance Specification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/property/specification.md): Formal specification for AdCP property governance — property models, feature evaluation, list management, and delivery validation. ##### Tasks - [Property Governance Tasks](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/property/tasks/index.md): Task reference for AdCP property governance — property list management, feature evaluation, and delivery validation tasks. - [Property List Management](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/property/tasks/property_lists.md): Property list tasks in AdCP create, update, get, list, and delete inclusion and exclusion lists combining static sets with dynamic filters. - [validate_property_delivery](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/property/tasks/validate_property_delivery.md): validate_property_delivery checks delivery records against a property list for compliance and supply path authorization in AdCP. #### Collection Governance - [Collection Governance](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/collection/index.md): AdCP Collection Governance enables program-level brand safety through collection lists — managed exclusion and inclusion lists for shows, series, and other content programs independent of which properties carry them. - [Collection List Management](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/collection/tasks/collection_lists.md): Collection list tasks in AdCP create, update, get, list, and delete inclusion and exclusion lists for content programs, combining explicit program references with dynamic genre and content rating filters. #### Content Standards - [Content Standards](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/index.md): AdCP Content Standards enable privacy-preserving brand suitability evaluation for AI-generated and ephemeral content that cannot leave publisher infrastructure. - [Content Artifacts](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/artifacts.md): Artifacts in AdCP represent the content context adjacent to ad placements, enabling brand suitability evaluation without exposing raw content. - [Content Standards Implementation](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/implementation-guide.md): Step-by-step guide to implementing AdCP Content Standards — calibration flow, artifact generation, delivery validation, and integration patterns. ##### Tasks - [list_content_standards](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/tasks/list_content_standards.md): list_content_standards returns available content safety configurations with optional filtering and pagination in AdCP. - [get_content_standards](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/tasks/get_content_standards.md): get_content_standards retrieves the full content safety policy configuration for a specific standards ID in AdCP. - [create_content_standards](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/tasks/create_content_standards.md): create_content_standards defines a brand suitability configuration with content policies, risk thresholds, and category rules for AdCP campaigns. - [update_content_standards](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/tasks/update_content_standards.md): update_content_standards modifies an existing content standards configuration in AdCP, creating a new version for audit purposes. - [calibrate_content](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/tasks/calibrate_content.md): calibrate_content aligns buyers and sellers on brand suitability standards through structured dialogue before AdCP campaign execution begins. - [get_media_buy_artifacts](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/tasks/get_media_buy_artifacts.md): get_media_buy_artifacts retrieves content context records from a media buy for post-delivery brand suitability validation in AdCP. - [validate_content_delivery](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/content-standards/tasks/validate_content_delivery.md): validate_content_delivery batch-evaluates delivery records against content safety policies asynchronously in AdCP. #### Creative Governance - [Creative Governance](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/creative/index.md): AdCP Creative Governance provides standardized creative evaluation — security scanning, AI provenance verification, and accessibility compliance checks. - [get_creative_features](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/creative/get_creative_features.md): get_creative_features evaluates a creative manifest against a governance agent and returns feature values for brand safety and compliance in AdCP. - [Provenance verification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/creative/provenance-verification.md): How AI provenance claims travel with creatives in AdCP and get independently verified at each enforcement point in the delivery chain. #### Campaign Governance - [Campaign Governance](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/index.md): AdCP Campaign Governance validates autonomous media buys against authorized plans, budget limits, and compliance policies using three-party trust. - [Safety Model](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/safety-model.md): AdCP three-party trust prevents any single AI agent from making unilateral media buying decisions. Orchestrator, governance, and seller validate independently. - [Specification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/specification.md): Formal specification for AdCP campaign governance — plan schemas, budget authority models, validation logic, and integration patterns. - [Audit trail: internal vs shareable views](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/audit-trail.md): How AdCP's campaign governance audit trail splits into a full internal view and scoped shareable views, and what each counterparty can safely see. ##### Tasks - [Task reference](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/tasks/index.md): Task reference for AdCP campaign governance — sync_plans, check_governance, report_plan_outcome, and get_plan_audit_logs. - [sync_plans](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/tasks/sync_plans.md): sync_plans pushes campaign plans with budget limits, channels, flight dates, and compliance policies to an AdCP governance agent. - [report_plan_outcome](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/tasks/report_plan_outcome.md): report_plan_outcome sends action results to the AdCP governance agent so it can update budget tracking, state, and compliance records. - [check_governance](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/tasks/check_governance.md): check_governance is the universal validation gate in AdCP — orchestrators and sellers call it before executing any campaign action. - [get_plan_audit_logs](https://docs.adcontextprotocol.org/dist/docs/3.1.24/governance/campaign/tasks/get_plan_audit_logs.md): get_plan_audit_logs retrieves governance state, budget tracking, and a complete audit trail for AdCP campaign plans or portfolios. ### Sponsored Intelligence - [Sponsored Intelligence](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/overview.md): Monetizing AI surfaces with AdCP — follow a growth marketer as she launches campaigns on an AI platform using the reversed data flow. - [Monetizing AI surfaces](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/monetizing-ai.md): A practical guide for brands, agencies, and small businesses who want to advertise on AI assistants, AI search engines, and other AI platforms. #### Concepts - [Product spectrum](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/product-spectrum.md): The four Sponsored Intelligence product types — sponsored responses, AI search results, generative display, and SI Chat Protocol brand experience handoffs — with JSON examples and pricing models. - [Ad networks](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/networks.md): How AI ad networks aggregate inventory across multiple AI platforms using AdCP — product modeling, account chains, catalog forwarding, governance, delivery reporting, and SI Chat Protocol routing. - [End-to-end workflow](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/workflow.md): The complete Sponsored Intelligence workflow — from account setup through catalog sync, product discovery, media buy creation, and delivery reporting. - [Measurement](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/measurement.md): Sponsored Intelligence measurement — engagement metrics, conversion tracking, and commerce in the conversation. #### SI Chat Protocol - [SI Chat Protocol](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/si-chat-protocol.md): The SI Chat Protocol defines conversational brand experiences in AI assistants — session lifecycle, capability negotiation, identity consent, UI components, and ACP commerce handoff. - [Implementing SI Agents](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/implementing-si-agents.md): Build an AdCP Sponsored Intelligence agent. Implement si_get_offering, si_initiate_session, si_send_message, and si_terminate_session as MCP tools to serve conversational brand experiences. - [Implementing SI Hosts](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/implementing-si-hosts.md): Integrate AdCP Sponsored Intelligence into your AI platform. Discover brand agents, render standard UI components, manage session lifecycle, handle consent flows, and hand off to ACP for commerce. #### Reference - [Sponsored Intelligence Specification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/specification.md): Formal AdCP Sponsored Intelligence specification. Session states, transport requirements, capability negotiation, standard UI components, identity and consent rules, commerce integration, and conformance criteria. - [Sponsored Intelligence Tasks](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/tasks/index.md): AdCP Sponsored Intelligence task reference. Four tasks covering the full session lifecycle: si_get_offering, si_initiate_session, si_send_message, and si_terminate_session with MCP and A2A transport examples. - [si_get_offering](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/tasks/si_get_offering.md): si_get_offering is the AdCP task for anonymous pre-session offering lookups. Retrieve offering details, matching products, and an offering token for session continuity — without requiring user PII. - [si_initiate_session](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/tasks/si_initiate_session.md): si_initiate_session is the AdCP task that starts a Sponsored Intelligence session. Pass user intent, consented identity, and host capabilities to a brand agent and receive a personalized response. - [si_send_message](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/tasks/si_send_message.md): si_send_message is the AdCP task for exchanging messages in an active SI session. Relay user text or action responses to the brand agent and handle active, pending_handoff, or complete session states. - [si_terminate_session](https://docs.adcontextprotocol.org/dist/docs/3.1.24/sponsored-intelligence/tasks/si_terminate_session.md): si_terminate_session is the AdCP task for ending an SI session. Supports five termination reasons including transaction handoff to ACP, with follow-up suggestions and checkout context for commerce. ### Brand - [Brand protocol](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/index.md): brand.json is the open standard that tells AI agents how to use your brand correctly. Publish logos, colors, tone, and restrictions in one machine-readable file that every agent in the AdCP ecosystem obeys. - [Brand protocol](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/key-concepts.md): AdCP brand protocol concepts: houses, brands, brand agents, Keller architecture types, brand.json discovery, resolution flow, and how brand identity feeds into creative generation and media buying. - [Rights licensing walkthrough](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/walkthrough-rights-licensing.md): AdCP rights licensing walkthrough: follow a buyer from campaign brief through talent discovery (get_rights), acquisition (acquire_rights), creative approval, and lifecycle management including extension and revocation. - [For advertisers](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/for-advertisers.md): License real talent for AI-generated ads through AdCP. Search for available athletes, musicians, and influencers with transparent pricing, then receive scoped generation credentials for AI creative tools. - [For talent and rights holders](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/for-rights-holders.md): How talent and rights holders control AI-generated likeness, voice, and endorsement use through AdCP. Scoped credentials, geographic limits, approval workflows, impression tracking, and long-tail licensing revenue. - [Seller setup](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/seller-setup.md): How publishers, sales agents, networks, and SSPs use brand.json and adagents.json together for seller identity, signing-key discovery, and supply path verification. - [brand.json Specification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/brand-json.md): brand.json specification for AdCP. File format, five variants (portfolio, redirect, agent, authoritative location, brand canonical document), brand definition fields, mutual-assertion trust model, visual guidelines, colorways, type scale, trademarks, and resolution algorithm. - [Building a brand agent](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/building-a-brand-agent.md): Build an AdCP brand agent as an MCP server. Serve brand identity via get_brand_identity, license talent rights via get_rights and acquire_rights, with public and authorized data tiers. - [UI guidance for rejected claims](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/ui-guidance.md): Non-normative consumer-side guidance for rendering verify_brand_claim disputed / not_ours rejections in DSPs, portfolio explorers, creative-clearance UIs, and brand-safety pipelines. Covers attribution language, recovery paths for the rejected publisher, audit trail recommendations, and legal-exposu… #### Tasks - [get_brand_identity](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/tasks/get_brand_identity.md): get_brand_identity is the AdCP task for retrieving brand data from a brand agent. Returns logos, colors, fonts, visual guidelines, tone, and voice synthesis config with public and authorized access tiers. - [verify_brand_claim](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/tasks/verify_brand_claim.md): verify_brand_claim is the unified AdCP brand-protocol task for asking a brand-agent whether a specific claim about its identity is owned, pending, disputed, or licensed. One tool, four claim types — subsidiary, parent, property, trademark — discriminated by a claim_type field. - [verify_brand_claims](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/tasks/verify_brand_claims.md): verify_brand_claims is the bulk variant of verify_brand_claim — verify many claims against one brand-agent in a single round-trip. Same four claim types (subsidiary, parent, property, trademark); results are returned positionally aligned with the request. - [get_rights](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/tasks/get_rights.md): get_rights is the AdCP task for discovering licensable talent, music, and stock media. Search with natural language, get matches with pricing options, and filter by buyer brand compatibility. - [acquire_rights](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/tasks/acquire_rights.md): acquire_rights is the AdCP task for binding rights acquisition. Submit a pricing option and campaign details to receive generation credentials, rights constraints, and disclosure requirements from a brand agent. - [update_rights](https://docs.adcontextprotocol.org/dist/docs/3.1.24/brand-protocol/tasks/update_rights.md): update_rights is the AdCP task for modifying active rights grants. Extend end dates, adjust impression caps, switch pricing options, or pause and resume — with re-issued generation credentials. ### Signals - [Signals protocol](https://docs.adcontextprotocol.org/dist/docs/3.1.24/signals/overview.md): Follow a media buyer from campaign brief to signal activation across automotive, geo, and retail data — a visual walkthrough of the AdCP signals workflow. - [Key concepts](https://docs.adcontextprotocol.org/dist/docs/3.1.24/signals/key-concepts.md): AdCP signal types (binary, categorical, numeric), signal references, discovery via get_signals, activation via activate_signal, and authorization through adagents.json. - [Signals ecosystem](https://docs.adcontextprotocol.org/dist/docs/3.1.24/signals/ecosystem.md): AdCP signals ecosystem: how data providers, retailers, publishers, CDPs, and identity companies expose and activate audience signals through the signals protocol. - [Data Provider Guide](https://docs.adcontextprotocol.org/dist/docs/3.1.24/signals/data-providers.md): Publish signal definitions as a data provider using adagents.json. Define signal value types, authorize signal agents, and enable AI-driven audience discovery and verification through AdCP. #### Reference - [Signals Specification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/signals/specification.md): Formal AdCP signals protocol specification. Transport requirements, get_signals and activate_signal task schemas, conformance criteria, error handling, activation key security, and RFC 2119 requirements. - [get_signals](https://docs.adcontextprotocol.org/dist/docs/3.1.24/signals/tasks/get_signals.md): get_signals is the AdCP task for discovering audience and contextual signals. Search by natural language or signal reference, filter by platform and CPM, and get real-time deployment status with activation keys. - [activate_signal](https://docs.adcontextprotocol.org/dist/docs/3.1.24/signals/tasks/activate_signal.md): activate_signal is the AdCP task for pushing audience segments to DSPs and sales agents. Supports async activation, deactivation for data governance, and returns platform-specific activation keys. ### Trusted Match - [Trusted Match Protocol](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/index.md): AdCP's real-time execution layer — follow a cross-publisher frequency capping story from wasted budget to structural privacy, across every surface. - [How demand reaches AI assistants](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/ai-mediation.md): A mediation protocol for AI assistants — how demand finds conversational AI when the context can't be broadcast to every buyer. - [TMP for Buyer Agents](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/buyer-guide.md): How buyer agents integrate with TMP — responding to Context Match and Identity Match requests, structuring offers, and managing frequency caps. - [The Execution Gap](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/execution-gap.md): Why existing protocols fail at real-time execution, and why TMP takes a matching approach instead of an auction approach. - [Context Match and Identity Match](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/context-and-identity.md): The two operations at the heart of TMP, how they work, and how the publisher joins them at decision time. - [TMP Specification](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/specification.md): Authoritative message type definitions, field tables, privacy requirements, and conformance levels for the Trusted Match Protocol. - [The TMP Router](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/router-architecture.md): Architecture and operation of the TMP Router, including single-binary design, integration paths, and fan-out. - [Privacy Architecture](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/privacy-architecture.md): How TMP separates user identity from page context, what each party can and cannot learn, and how TEE attestation upgrades the guarantee. - [Data Protection Roles](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/data-protection-roles.md): How TMP's architecture maps to GDPR controller/processor roles — what each party determines, what data each party holds, and where the risks are. - [Migrating from AXE to TMP](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/migration-from-axe.md): How to migrate from AXE segment targeting to TMP's offer and eligibility model — concept mapping, parallel operation, and cutover. #### Surface Guides - [TMP for Web Publishers](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/surfaces/web.md): How TMP activates pre-negotiated packages on web pages using Prebid and GAM. - [TMP for CTV](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/surfaces/ctv.md): How TMP activates packages for CTV pod composition with creative variant selection. - [TMP for Mobile Apps](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/surfaces/mobile.md): How TMP integrates with mobile mediation SDKs to activate pre-negotiated AdCP packages alongside programmatic demand. - [TMP for Retail Media](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/surfaces/retail-media.md): How TMP activates sponsored product packages with GTIN-level catalog refinement. - [TMP for AI Assistants](https://docs.adcontextprotocol.org/dist/docs/3.1.24/trusted-match/surfaces/ai-assistants.md): How TMP enables monetization of AI chat and assistant surfaces without traditional ad servers.