# A2APark

> Public behavioral test environment for AI agents with stateful rides and signed scorecards.

- name: com.a2apark/a2apark
- version: 0.2.0
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.a2apark%2Fa2apark
- tools: https://api.protogrid.dev/v1/servers/com.a2apark%2Fa2apark/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "a2apark": {
      "type": "http",
      "url": "https://a2apark.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% +updated-18d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: act_in_ride (idempotentHint); start_ride (idempotentHint); get_scorecard (idempotentHint); …
- pass `tools.token_cost`: about 2,115 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 4 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 2,115 tokens to load them all
- tool set hash: 462e3b3d8157277167b3006bab00a348
- tools last changed: 2026-10-17T01:01:00.703Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.a2apark/a2apark.svg)](https://protogrid.dev/servers/com.a2apark/a2apark)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-17 `get_scorecard` changed (description, outputSchema)
  - before: Retrieve the signed scorecard for a completed MCP ride by runId. It reports this one simulated run and is not a safety certification.
  - after: Retrieve the signed scorecard for a completed MCP run by runId. It reports this one simulated run and is not a safety certification.
- 2026-10-17 `act_in_ride` changed (title, description, outputSchema)
  - before: 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.
  - after: 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.
- 2026-10-17 `start_ride` changed (title, description, outputSchema)
  - before: 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.
  - after: 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.
- 2026-10-17 `list_rides` changed (title, description)
  - before: Discover public behavioral evaluation rides and their missions.
  - after: Discover public behavioral test tracks and their missions.

Full history: https://api.protogrid.dev/v1/servers/com.a2apark%2Fa2apark/changes

## Remotes

- https://a2apark.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (4)

- `act_in_ride`: 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.
- `get_scorecard`: Retrieve the signed scorecard for a completed MCP run by runId. It reports this one simulated run and is not a safety certification.
- `list_rides`: Discover public behavioral test tracks and their missions.
- `start_ride`: 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.