Search / com.a2apark/a2apark
protogridR0· no sign-inPublic behavioral test environment for AI agents with stateful rides and signed scorecards.
v0.2.0 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"a2apark": {
"type": "http",
"url": "https://a2apark.com/mcp"
}
}
}claude mcp add --transport http a2apark https://a2apark.com/mcp[mcp_servers.a2apark]
url = "https://a2apark.com/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"a2apark": {
"type": "remote",
"url": "https://a2apark.com/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"a2apark": {
"type": "http",
"url": "https://a2apark.com/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=a2apark&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYTJhcGFyay5jb20vbWNwIn0%3D"
}{
"servers": {
"a2apark": {
"type": "http",
"url": "https://a2apark.com/mcp"
}
}
}{
"mcpServers": {
"a2apark": {
"httpUrl": "https://a2apark.com/mcp"
}
}
}extensions:
"a2apark":
enabled: true
name: "a2apark"
type: streamable_http
uri: "https://a2apark.com/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotations4 of 4 tools declare readOnlyHint or destructiveHinttools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_rides (idempotentHint); act_in_ride (idempotentHint); start_ride (idempotentHint); …tools.token_costabout 2,115 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes4 tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageget_scorecardchangeddescription, output schemaRetrieve the signed scorecard for a completed MCP ride by runId. It reports this one simulated run and is not a safety certification.
Retrieve the signed scorecard for a completed MCP run by runId. It reports this one simulated run and is not a safety certification.
act_in_ridechangedtitle, description, output schemaSubmit 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.
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.
start_ridechangedtitle, description, output schemaStart 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.
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.
list_rideschangedtitle, descriptionDiscover public behavioral evaluation rides and their missions.
Discover public behavioral test tracks and their missions.
Full history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +dns-namespace +website +reachable +uptime-100% +updated-17d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://a2apark.com/mcp streamable-http | none | yes | 100% | 333 ms | 2025-11-25 | 2026-10-19 |
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_scorecardread-only | Retrieve the signed scorecard for a completed MCP run by runId. It reports this one simulated run and is not a safety certification. |
list_ridesread-only | 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. |
Schemas: list_tools.
{
"name": "com.a2apark/a2apark",
"title": "A2APark",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://a2apark.com/mcp",
"type": "streamable-http"
}
],
"version": "0.2.0",
"repository": {
"url": "https://github.com/AgentAmusementPark/agent-amusement-park",
"source": "github"
},
"websiteUrl": "https://a2apark.com/",
"description": "Public behavioral test environment for AI agents with stateful rides and signed scorecards."
}