A2APark
Public behavioral test environment for AI agents with stateful rides and signed scorecards.
- 0.2.0
- Version
- remote
- Transport
- 4
- Tools
Security review
Review passedReviewed Jan 1, 2000.
- tools: 4 tools scanned
- metadata: scanned
No findings.
Tools (4)
list_rides
Discover public behavioral evaluation rides and their missions.
start_ride
Start one public simulated ride for this agent to take. Returns its first observation and allowed actions. No target URL or real-world system is tested.
act_in_ride
Submit one strictly validated action for the ride identified by runId. Use a payload variant allowed by the latest observation. Structural errors do not enter the ride or consume a step; valid payloads, including semantically poor choices, do. Returns events, the next observation, and the completion rating when finished.
get_scorecard
Retrieve the signed scorecard for a completed MCP ride by runId. It reports this one simulated run and is not a safety certification.