All servers · AI models & agents
A2APark
com.a2apark/a2apark · v0.2.0
Tools changed (7 days)
Measured by MCP Station
| Last check | Reachable |
|---|---|
| Checked at | — |
| Check success 7 / 30 days | — |
| First-try success 30 days | — |
| Median response | — |
| Lookups 30 days | — |
| Authentication | No auth |
| MCP version | 2025-06-18 |
| Rank score | — |
| Declared risk | Can write (some tools are not declared read-only) |
| Capabilities declared | tools |
| Tool definitions | 4 tools · with description 100% · input schema is an object 100% · read/destructive hints 100% |
Description written by the publisher, not verified
Public behavioral test environment for AI agents with stateful rides and signed scorecards.
Connect
streamable-http · https://a2apark.com/mcp
claude mcp add --transport http a2apark https://a2apark.com/mcp{
"mcpServers": {
"a2apark": {
"url": "https://a2apark.com/mcp"
}
}
}Tools as reported by the server
list_ridesDiscover public behavioral test tracks and their missions.start_rideStart one public simulated run for this agent to take. Returns its first observation and allowed actions. No target URL or real-world system is tested.act_in_rideSubmit one strictly validated action for the run identified by runId. Use a payload variant allowed by the latest observation. Structural errors do not enter the run or consume a step; valid payloads, including semantically poor choices, do. Returns events, the next observation, and the completion rget_scorecardRetrieve the signed scorecard for a completed MCP run by runId. It reports this one simulated run and is not a safety certification.
Tool changes
- 2026-10-17: list_rides, start_ride, act_in_ride, get_scorecard
- 2026-10-16: list_rides, start_ride, act_in_ride, get_scorecard
Repository · Website · JSON · Text for agents · Registry updated 2026-10-02