protogrid

Search / io.github.evalgate/evalgate

EvalGate

R1· needs a key

Create and run AI evaluations, record traces, and inspect results with scoped organization access.

v1.0.0 · active · website · descriptor JSON · versions

An agent can connect on its own if it already holds EVALGATE_API_KEY.Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.
Quality94new
Trust80of 100
Uptime, 30 days100%
Latency p501093 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "evalgate": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${EVALGATE_API_KEY}"
      }
    }
  }
}
claude mcp add --transport http evalgate https://www.evalgate.com/api/mcp --header "Authorization: Bearer ${EVALGATE_API_KEY}"
[mcp_servers.evalgate]
url = "https://www.evalgate.com/api/mcp"
bearer_token_env_var = "EVALGATE_API_KEY"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "evalgate": {
      "type": "remote",
      "url": "https://www.evalgate.com/api/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:EVALGATE_API_KEY}"
      }
    }
  }
}
{
  "mcpServers": {
    "evalgate": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${EVALGATE_API_KEY}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=evalgate&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd3d3LmV2YWxnYXRlLmNvbS9hcGkvbWNwIiwiaGVhZGVycyI6eyJBdXRob3JpemF0aW9uIjoiQmVhcmVyICR7RVZBTEdBVEVfQVBJX0tFWX0ifX0%3D"
}
{
  "servers": {
    "evalgate": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${EVALGATE_API_KEY}"
      }
    }
  }
}
{
  "mcpServers": {
    "evalgate": {
      "httpUrl": "https://www.evalgate.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${EVALGATE_API_KEY}"
      }
    }
  }
}
extensions:
  "evalgate":
    enabled: true
    name: "evalgate"
    type: streamable_http
    uri: "https://www.evalgate.com/api/mcp"
    headers:
      "Authorization": "Bearer ${EVALGATE_API_KEY}"
    timeout: 300

Placeholders to fill from your own secret store: ${EVALGATE_API_KEY}. The registry never accepts secret values.

Quality 94 / 100new

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene100 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations12 of 12 tools declare readOnlyHint or destructiveHint
  • pass
    tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
  • pass
    tools.token_costabout 1,896 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history recorded for 0 of the 7 days needed
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

12 tools, about 1,896 tokens to load them all · tool set 37fc1e45d8e3 · checked 2026-10-19 11:27 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

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.

Trust 80 / 100

no-repository
provenance45
liveness100
freshness100
hygiene80

+website +reachable +uptime-100% +updated-1d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://www.evalgate.com/api/mcp streamable-httpapi_key ${EVALGATE_API_KEY}yes100%1093 ms2026-07-282026-10-19

Tools (12)

baseline.lineageread-onlyShow the published baseline anchor and its evidence lineage.
connections.catalogread-onlyInspect all connector definitions and exact installed setup paths. Unavailable blueprints and live verification are separate facts.
connections.graphread-onlyRead canonical connection references and currently visible exact resource revisions. No source access grant or execution.
connections.listread-onlyList current workspace connection metadata, with source restrictions, freshness and bounded continuation. Does not reveal secrets or grant source access.
connections.rootsread-onlyPage independent configured account roots using current administrator authority. Does not list secrets or imply verified connector availability.
connector.healthread-onlyShow the latest connector-readiness reports for the organization.
docs.searchread-onlySearch the published OpenAPI operation catalog for relevant help.
evaluations.listread-onlyList evaluations with a stable cursor for the organization.
project.inspectread-onlyInspect the evaluations and project keys available in the authenticated organization.
project.planread-onlyReturn a non-mutating next-step plan for connecting a repository, evaluation, or trace source.
run.explainread-onlyExplain a run using its status, failed-case metadata, and evidence-lineage summary.
runs.listread-onlyList evaluation runs with stable cursors and regression signals.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.evalgate/evalgate",
  "title": "EvalGate",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://www.evalgate.com/api/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "value": "Bearer {EVALGATE_API_KEY}",
          "isSecret": true,
          "variables": {
            "EVALGATE_API_KEY": {
              "format": "string",
              "isSecret": true,
              "isRequired": true,
              "description": "Your EvalGate organization API key. Available operations depend on its scopes and your role."
            }
          },
          "isRequired": true,
          "description": "Authenticate with an EvalGate organization API key."
        }
      ]
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://www.evalgate.com/docs/platform/mcp-integration",
  "description": "Create and run AI evaluations, record traces, and inspect results with scoped organization access."
}