Skip to content

A2APark

by a2apark.com · remote · no sign-in to list tools · v0.2.0 · published by com.a2apark

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

Changes · 2
CompareRegistry entry

4 tools: 2 change things and 2 only read.

Scanned Oct 21, 2026

3 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http a2apark https://a2apark.com/mcp

Findings

Matches of fixed checks, with the text they matched.

3 warn
  • Warnact_in_ride

    The input schema at properties.action.anyOf[2].anyOf[2].properties.revision.$ref contains a 54-character base64 string.

    Matched text

    inputSchema.properties.action.anyOf[2].anyOf[2].properties.revision.$ref: "#/properties/action/anyOf/2/anyOf/1/properties/revision"

    What this check looks for
  • Warnact_in_ride

    The input schema at properties.action.anyOf[2].anyOf[3].properties.revision.$ref contains a 54-character base64 string.

    Matched text

    inputSchema.properties.action.anyOf[2].anyOf[3].properties.revision.$ref: "#/properties/action/anyOf/2/anyOf/1/properties/revision"

    What this check looks for
  • Warnact_in_ride

    The input schema at properties.action.anyOf[2].anyOf[4].properties.revision.$ref contains a 54-character base64 string.

    Matched text

    inputSchema.properties.action.anyOf[2].anyOf[4].properties.revision.$ref: "#/properties/action/anyOf/2/anyOf/1/properties/revision"

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 2Claude Code: ask
  • act_in_rideSubmit one strictly validated action for the run identified by runId.3 findings

    Why it is in this group

    • The description's first verb is "submit": a word for a change.

    Findings

    • Warn

      The input schema at properties.action.anyOf[2].anyOf[2].properties.revision.$ref contains a 54-character base64 string.

      Matched text

      inputSchema.properties.action.anyOf[2].anyOf[2].properties.revision.$ref: "#/properties/action/anyOf/2/anyOf/1/properties/revision"

      What this check looks for
    • Warn

      The input schema at properties.action.anyOf[2].anyOf[3].properties.revision.$ref contains a 54-character base64 string.

      Matched text

      inputSchema.properties.action.anyOf[2].anyOf[3].properties.revision.$ref: "#/properties/action/anyOf/2/anyOf/1/properties/revision"

      What this check looks for
    • Warn

      The input schema at properties.action.anyOf[2].anyOf[4].properties.revision.$ref contains a 54-character base64 string.

      Matched text

      inputSchema.properties.action.anyOf[2].anyOf[4].properties.revision.$ref: "#/properties/action/anyOf/2/anyOf/1/properties/revision"

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • start_rideStart one public simulated run for this agent to take.No findings

    Why it is in this group

    • The name "start_ride" says "start": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
Only reads 2Claude Code: allow
  • get_scorecardRetrieve the signed scorecard for a completed MCP run by runId.No findings

    Why it is in this group

    • The name "get_scorecard" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve the signed scorecard for a completed MCP run by runId. It reports this one simulated run and is not a safety certification.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • list_ridesDiscover public behavioral test tracks and their missions.No findings

    Why it is in this group

    • The name "list_rides" says "list": a word for reading.
    Description, as the server wrote it
    Discover public behavioral test tracks and their missions.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http a2apark https://a2apark.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__a2apark__list_rides",
      "mcp__a2apark__get_scorecard"
    ],
    "ask": [
      "mcp__a2apark__start_ride",
      "mcp__a2apark__act_in_ride"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as a2apark. Review it before you use it.