Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "access_check_url", "access_explain_verdicts" and "access_list_agents"
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true ⟨9 unchanged words⟩
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true ⟨5 unchanged words⟩
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true ⟨7 unchanged words⟩
Recently observed → Live
Changed the definition of "access_check_url", "access_explain_verdicts" and "access_list_agents"
Given a URL, saySays whether an AI agent may fetchita URL, on what terms, and at what price. ⟨120 unchanged words⟩
⟨5 unchanged words⟩ ,"properties":{"includeEvidence":{"description":"IncludeWhen true, the answer includes every request made, with status and headers ( ⟨6 unchanged words⟩ :"boolean"},"skipWellKnown":{"description":"SkipWhen true,
Live → Recently observed
Verified owner set by well_known_file proof on agentwares-access-index.vercel.app
Unknown → Live
Listed separately from agentcheck. Checks before this date are on that record.
Showing the latest 7 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true,"title":"Check whether an agent may fetch a URL"}
ReturnReturns the five verdictsthis indexaccess_check_url canreturngive, what each one means for an agent that has just been refused, andwhattheagent'snext moveisforeach.each,Costsplusnothingwhatandeach confidence level rests on. Free, makes norequest;networkcallrequest, and returns the same answer every time: itonceis the key tointerpretreading access_check_url results.
{"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"What the verdicts mean"}
ReturnReturns the AI crawler tokens this index reads robots.txt ⟨15 unchanged words⟩ operator sends, which make a robots ruleunenforceable.unenforceable, and the list of verdict names. Useful when writing or auditing a robots.txt.
{"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"AI user-agents this index reports on"}