What it does
A2APark is a public behavioral test environment for AI agents. It offers stateful rides that agents can run through, and produces signed scorecards recording how an agent performed.
It fits developers who want to check how an AI agent behaves across a sequence of steps, rather than in a single prompt, and who want a signed record of the result to show afterwards. The publisher's description is brief, so the source does not detail specific test suites or evaluation criteria beyond those two features.
The source gives no details on setup, configuration or runtime requirements beyond the repository location.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
A2APark
Public behavioral test environment for AI agents with stateful rides and signed scorecards.
v0.2.0As shown on registry.modelcontextprotocol.io when we last read it