One address for AdCP.
The Advertising Context Protocol is an open protocol for agentic advertising: it defines the tasks and schemas advertising agents use to discover inventory, set up accounts, buy media, manage creative, activate signals, apply governance and report results — carried over MCP and A2A rather than over a UI.
This site tracks AdCP from the implementer seat, not the spectator seat: a vendor-neutral guide to the spec, a dated record of who has actually shipped an agent, two agents of its own that anyone can call, and the essays arguing about where it goes. Evgeny Popov is an AdCP founding member and co-leads the protocol’s Signals & Measurement working group — a seat on one working group, not a claim to speak for the protocol.
What each surface is for.
One reference page, one live record, two things you can run, three builds. Read left to right: what the protocol says, what the market has shipped, what a call actually looks like, and what it took to ship one.
- Reference
What the protocol is, the domains it defines, what changed in 3.1, and a 3.0 → 3.1 implementation checklist. Vendor-neutral, every claim sourced.
- Live record
Who has actually shipped an agent — the public registry kept as a dated record, searchable by type, with real request/response captures and adagents.json explained.
- Manual
How to buy display inventory from a live seller agent: discovery, briefs, media buys, creatives, the human gate, delivery reporting. Every curl and PowerShell call copy-pasteable.
- Live demo
Type an audience brief, press Run, and read the actual JSON-RPC frames on the wire. Nothing mocked; the buy step is a copy-to-clipboard snippet, never executed.
- Build · publisher
One publisher running the whole loop: a live seller agent, a minimal ad server, session-scoped synaptic audiences, human-gated approvals, honest delivery numbers.
- Build · signals
The MIT-licensed signals data provider behind this site’s registry listing — production demo at adcp.signal-stack.io, source and issues on GitHub.
- Build · prototype
An experimental visual prototype of agentic orchestration: connected agent roles coordinating signals, identity, governance, creative, buying and measurement around a live brief.
Essays on AdCP.
Every public essay that names AdCP in its title or summary, newest first — pulled from the writing collection, so this list cannot go stale.
- Jul 2026 #1 most read · 30d
AdCP vs AAMP: The Retrofit and the Greenfield
Two agentic advertising standards shipped within 48 hours of each other in late July — AdCP tagged v3.1.8, IAB Tech Lab announced AAMP 2.3. The trade press calls it a war and mislabels the battlefield. Read at the repository level, the real difference isn't altitude (both negotiate deals; both touch the impression path). It's ancestry: AAMP retrofits agents onto advertising's existing rails — OpenDirect, OpenRTB, the ad servers and DSPs already in production — while AdCP writes a new campaign-lifecycle protocol with trust in the wire format. Every claim verified against the repos and specs, both directions, with the press-release-vs-repository deltas printed for each side.
- Jul 2026
The Prebid Sales Agent: AdCP's Sell Side Lands in the Wrapper
AdCP's sell side is a deal machine beside the wrapper, not inside it — the architecture, the deal loop, five publisher decisions, the caveats nobody prints.
- Jun 2026 #5 most read · 30d
Notes from the Implementer Seat
What running a live AdCP signals agent teaches you that reading the spec never will.
- Feb 2026
The Missing Link in Ad Tech: How UCP & AdCP Are Finally Unifying the "Alphabet Soup"
How UCP and AdCP retire ad-tech's "Tower of Babel" — Architect (intent) and Engineer (math) of the agentic stack.
- Nov 2025
AdCP: The Open Standard for Agentic Advertising
Connect once. Operate anywhere.
The rest of the stack.
AdCP is one layer. It sits on transaction rails, inside privacy constraints, and is judged by measurement it does not own.
Deciding what to expose to AdCP — and what to hold back?
Sales, signals, creative, or nothing yet: the decision turns on governance, conformance, and what you can measure afterwards. Advisory for AdTech, MarTech, data, AI, and media technology companies moving from AI pilots to governed agentic workflows.