Skip to content
MCP server

EvalGate Docs

Search and read EvalGate's public documentation from an AI client

Install
Pricing
Freemium
Platforms
API, Web
Runs
Remotely
Version
1.0.0
Listing updated
2 days ago

About EvalGate Docs

EvalGate Docs is a freemium MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.

This endpoint is the docs-only side of EvalGate's MCP setup. It needs no account or credential and only reads, so an assistant can look up how EvalGate's evaluation platform works before writing code against it.

EvalGate also runs a separate product endpoint at /api/mcp that is authenticated and permission-filtered. Its documented write tools include evaluations_create, test_cases_add, runs_start and traces_create, each tied to a role and a scope such as eval:write or runs:write. Anonymous clients cannot execute those, and the docs warn that an older /api/mcp/tools and /api/mcp/call pair is a separate proprietary HTTP Tool API.

The example configs show both servers side by side for Claude Code and Cursor, with the product server taking a bearer API key.

Install

Run in a terminal

claude mcp add --transport http evalgate-docs https://www.evalgate.com/api/mcp/docs

Add to Settings → Connectors → Add custom connector

https://www.evalgate.com/api/mcp/docs
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "evalgate-docs": {
      "url": "https://www.evalgate.com/api/mcp/docs"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "evalgate-docs": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp/docs"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "evalgate-docs": {
      "serverUrl": "https://www.evalgate.com/api/mcp/docs"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "evalgate-docs": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp/docs"
    }
  }
}

What it does

Public docs search
Look up EvalGate documentation without signing in.
Read-only access
The docs endpoint cannot change anything in an account.
Paired product endpoint
A second, authenticated server exposes evaluation, test case, run and trace tools.
Scoped writes
Product writes need a minimum role and scopes such as eval:write or runs:write.
Client config examples
Ready-made snippets for Claude Code and Cursor.

Good for

  • Ask an assistant how to set up an EvalGate evaluation
  • Check which scope a run needs before starting it
  • Wire the docs and product servers into a coding agent
  • Look up how traces and retention are handled

Pricing

Freemium

Docs server free; EvalGate plans: Developer $0 (1,000 results), Team $99, Scale $499, Business $1,500 per month

Prices change. Check evalgate.com before you buy.

EvalGate Docs FAQ

Do I need an account to use the docs server?

No. The registry entry says it is read-only with no account or credential needed.

Can the docs server start evaluation runs?

No. Running tools live on the separate authenticated product endpoint.

What does EvalGate charge?

Its pricing page lists a free Developer plan with 1,000 results a month, then $99 Team, $499 Scale and $1,500 Business plans; extra results cost $1 per 1,000.

Who pays for model usage?

The pricing page says model costs stay on your own provider bill with no markup.

Is EvalGate Docs free?

EvalGate Docs has a free plan, with paid plans for more usage or features.

How do I add EvalGate Docs to Claude Code?

Run this command in your terminal: claude mcp add --transport http evalgate-docs https://www.evalgate.com/api/mcp/docs

What are the best alternatives to EvalGate Docs?

The closest alternatives to EvalGate Docs are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to EvalGate Docs

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools