Websites that work with visiting agents.
A human visitor converts through persuasion. An agent is immune to persuasion; it converts through exchange. The Agent Surface encodes that exchange as WebMCP tools: every tool gives the agent a real capability and gives the site a real signal, by contract.
WebMCP 0 tools live on this page In production on 3 real sites MIT
What tools does this site offer? Call about_this_surface.
Works in ChatGPT's desktop browser today, or Chrome 149+ with
chrome://flags/#enable-webmcp-testing enabled.
The exchange ledger
| Stage | The agent gets | The site gets |
|---|---|---|
| Answer | Canonical facts in one call | Intent with declared purpose |
| Fit | An answer computed for its buyer | A self-qualified account, no form |
| Work | The site does part of the agent's job | Deep engagement a human watches |
| Advance | A computed offer, or a capability to keep | A transaction, attributed |
Three archetypes, three live demos
Search a real 100M-company graph anonymously, build a target list in a workspace the human watches, then claim the work by connecting the vendor's MCP. Reference: graph8.com.
Market size, channel benchmarks with their basis, case-study proof: a feasibility brief instead of a discovery call. Reference: cience.com.
Score a team against a published standard; benchmarks return with citations preformatted. Reference: tenbound.com.
The honesty rule
Agents remember, retry, and tell their users which sources burned them. An Agent Surface answers "not a fit" when that is true, labels model assumptions as assumptions, quotes observed numbers as ranges with attribution, and marks the untested as untested. It costs one bad-fit lead and buys the successor to SEO ranking: agent trust.