1. Conduid
  2. Analytics
  3. Opik MCP Server
MCP server · Analytics

Opik MCP Server

Building Production-Ready AI Agent Evaluation with Opik MCP Server on AWS AgentCore

37Low

Scored 7 days ago · breakdown

About Opik MCP Server

Opik MCP Server is an MCP server in the Analytics category: building Production-Ready AI Agent Evaluation with Opik MCP Server on AWS AgentCore.

The repository has 2 stars and 0 forks.

Install

Claude Code
claude mcp add opik-mcp-server -- npx -y opik-mcp
npx
npx -y opik-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (1)

read_skillRead one of the Opik agent skills bundled with this server

Parameters not published.

Ask AI

✦

Ask AI about Opik MCP Server

Powered by Claude · Grounded in docs

I know everything about Opik MCP Server. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

License Node.js Version TypeScript

[!IMPORTANT] This repository ships the MCP server implementation only. We do not currently provide a hosted remote MCP service for Opik. If you run streamable-http remotely, authentication is fail-closed by default.

Why this server

Opik MCP Server gives MCP-compatible clients one interface for:

  • Prompt lifecycle management
  • Workspace, project, and trace exploration
  • Metrics and dataset operations
  • MCP resources and resource templates for metadata-aware flows

Quickstart

1. Run with npx

# Opik Cloud
npx -y opik-mcp --apiKey YOUR_API_KEY

For self-hosted Opik, pass --apiUrl (for example http://localhost:5173/api) and use your local auth strategy.

2. Add to your MCP client

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "opik": {
      "command": "npx",
      "args": ["-y", "opik-mcp", "--apiKey", "YOUR_API_KEY"]
    }
  }
}

VS Code / GitHub Copilot (.vscode/mcp.json):

{
  "inputs": [
    {
      "type": "promptString",
      "id": "opik-api-key",
      "description": "Opik API Key",
      "password": true
    }
  ],
  "servers": {
    "opik-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "opik-mcp", "--apiKey", "${input:opik-api-key}"]
    }
  }
}

Windsurf (raw config):

{
  "mcpServers": {
    "opik": {
      "command": "npx",
      "args": ["-y", "opik-mcp", "--apiKey", "YOUR_API_KEY"]
    }
  }
}

More client-specific examples: docs/ide-integration.md

Run from source

git clone https://github.com/comet-ml/opik-mcp.git
cd opik-mcp
npm install
npm run build

Optional local config:

cp .env.example .env

Start the server:

npm run start:stdio
npm run start:http

Transport modes

Transport Use case Command
stdio Local MCP integration (same machine as client) npm run start:stdio
streamable-http Remote/self-hosted MCP endpoint (/mcp) npm run start:http

Remote auth defaults (streamable-http)

  • Authorization: Bearer <OPIK_API_KEY> or x-api-key is required by default.
  • Workspace is resolved server-side (token map recommended); workspace headers are not trusted by default.
  • In remote mode, request-context workspace takes precedence over tool workspaceName.
  • Missing or invalid auth returns HTTP 401.

Key environment flags:

  • STREAMABLE_HTTP_REQUIRE_AUTH (default true)
  • STREAMABLE_HTTP_VALIDATE_REMOTE_AUTH (default true, except test env)
  • REMOTE_TOKEN_WORKSPACE_MAP (JSON token-to-workspace map)
  • STREAMABLE_HTTP_TRUST_WORKSPACE_HEADERS (default false)

Deep dive: docs/streamable-http-transport.md

Toolsets

Toolsets let you narrow which capabilities are enabled:

  • core
  • integration
  • expert-prompts
  • expert-datasets
  • expert-trace-actions
  • expert-project-actions
  • metrics
  • all (enables all modern toolsets)

Configure via:

  • CLI: --toolsets all
  • Env: OPIK_TOOLSETS=core,expert-prompts,metrics

Details: docs/configuration.md

MCP resources and prompts

  • resources/list exposes static URIs (for example opik://workspace-info)
  • resources/templates/list exposes dynamic URI templates (for example opik://projects/{page}/{size})
  • resources/read supports static and templated URIs
  • prompts/list and prompts/get expose workflow prompts

Development

# Lint
npm run lint

# Test
npm test

# Build
npm run build

# Run precommit checks
make precommit

Documentation

Contributing

Please read CONTRIBUTING.md before opening a PR.

Citation

If you use this project in research, cite:

Comet ML, Inc, Koc, V., & Boiko, Y. (2025). Opik MCP Server. Github. https://doi.org/10.5281/zenodo.15411156

BibTeX:

@software{CometML_Opik_MCP_Server_2025,
  author = {{Comet ML, Inc} and Koc, V. and Boiko, Y.},
  title = {{Opik MCP Server}},
  year = {2025},
  publisher = {GitHub},
  url = {https://doi.org/10.5281/zenodo.15411156},
  doi = {10.5281/zenodo.15411156}
}

Citation metadata is also available in CITATION.cff.

License

Apache 2.0

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About Opik MCP Server

How do I install Opik MCP Server?

Run claude mcp add opik-mcp-server -- npx -y opik-mcp, then add the server to your MCP client's configuration.

Is Opik MCP Server safe to use with an AI agent?

Its trust score is 37 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Opik MCP Server still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.