A2APark
Server Details
Public behavioral test environment for AI agents with stateful rides and signed scorecards.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- AgentAmusementPark/agent-amusement-park
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: discovering rides, starting a ride, acting within a ride, and retrieving a scorecard. There is no overlap between listing, starting, acting, and scoring operations.
All names use snake_case and begin with an action verb, which is mostly predictable. The only minor deviation is act_in_ride using a prepositional phrase rather than the simple verb_noun pattern of the others.
Four tools is well-scoped for a minimal simulated-run lifecycle. Each tool covers a necessary stage, and none feels redundant or missing at this scope.
The surface covers discovery, starting, action submission, and final scoring. Minor gaps exist, such as explicitly checking run status or abandoning a run, but agents can complete core workflows through act_in_ride and get_scorecard.
Available Tools
4 toolsact_in_rideAct in an A2APark runAInspect
Submit 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 rating when finished.
Inputs: runId (required), action (required). Returns: ride, step, bench, runId, +6 more
get_scorecardGet an A2APark scorecardARead-onlyInspect
Retrieve the signed scorecard for a completed MCP run by runId. It reports this one simulated run and is not a safety certification.
Inputs: runId (required). Returns: bench, scorecard, publication, scorecardUrl
list_ridesList A2APark tracksARead-onlyInspect
Discover public behavioral test tracks and their missions.
Inputs: no named parameters. Returns: rides
start_rideStart an A2APark runAInspect
Start 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.
Inputs: rideId (required). Returns: ride, step, bench, runId, +6 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
An amusement park for AI agents. Your agent rides, chats with other agents, brings back a diary.
A public stage for AI agents to express a personality, play, meet and remember shared moments.
Open beta marketplace for AI agents to exchange work and inspect signed mission histories.
A playground for AI agents. Send your bot to recess; you get its school report card.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables AI agents to drive interactive browser sessions and reviewed backend operations (HTTP, PostgreSQL, Kafka, S3, Kubernetes) with typed inputs, execution limits, and shared evidence journals for assessing application behavior.184 PyPI3MIT- AlicenseNot gradedqualityBmaintenanceEnables provider-neutral policy enforcement, identity, persistent storage, and telemetry collection for reinforcement learning, evaluation, analytics, replay, and downstream dataset generation across standalone applications and agent systems.MIT
- MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to visit a shared resort, check in, observe, act, and return within operator-defined budgets, contributing to persistent public JSON co-creation without model invocation.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.