Skip to content
A2APark logo

A2APark MCP server

Which servers in the official MCP registry are A2APark's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-24

← Back to A2APark

Whose server it is
  • Registry namecom.a2apark/a2aparkverified in the MCP registry

The registry name sits under a2apark.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools4
  • Server calls itselfa2apark
  • Server version0.2.0
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 53 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: run an agent through simulated scenarios and inspect its actions; review scorecards showing mission completion and flagged actions; see where an agent succeeds or fails under controlled conditions.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "run an agent through simulated scenarios and inspect its actions", the likely first call is list_rides.
  • For "review scorecards showing mission completion and flagged actions", the likely first call is get_scorecard.
  • For "see where an agent succeeds or fails under controlled conditions", the likely first call is list_rides.
  • Parameters are untyped or undescribed in 3 of 4 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer124 ms
  • Space in an agent's context≈ 2,092 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsB · 88 of 100
  • Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 4

What an agent can do with it

  • can do · run an agent through simulated scenarios and inspect its actions
  • can do · review scorecards showing mission completion and flagged actions
  • can do · see where an agent succeeds or fails under controlled conditions

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers4 tools · read 2026-10-24
  • 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.

  • 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…

  • 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.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://a2apark.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.