Opik MCP Server: Seamless IDE Integration for AI Model Context

Summary
The Opik MCP Server provides a Model Context Protocol (MCP) implementation for Opik, enabling seamless integration with various IDEs. It offers a unified interface for managing prompt lifecycles, exploring workspaces, projects, and traces, and handling metrics and dataset operations. This server enhances developer workflows by centralizing access to critical AI development resources.
Repository Info
Tags
Click on any tag to explore related repositories
Introduction
The Opik MCP Server, developed by Comet ML, is a crucial component for integrating Opik with your favorite IDEs. It implements the Model Context Protocol (MCP), providing a standardized way to access and manage AI development resources directly within your development environment. This server supports both local stdio and remote streamable-http transports, offering flexibility for various setups.
Installation
To get started with Opik MCP Server, you can quickly run it using npx.
# For Opik Cloud
npx -y opik-mcp --apiKey YOUR_API_KEY
For self-hosted Opik instances, remember to pass the --apiUrl argument (e.g., http://localhost:5173/api) and use your local authentication strategy.
Examples
Integrating Opik MCP Server into your development workflow is straightforward. Here are examples for popular MCP-compatible clients:
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}"]
}
}
}
Why Use It
The Opik MCP Server streamlines AI development by providing a single, unified interface for several critical operations:
- Prompt Lifecycle Management: Efficiently manage and track the evolution of your prompts.
- Workspace, Project, and Trace Exploration: Easily navigate and understand your AI projects, experiments, and execution traces.
- Metrics and Dataset Operations: Access and manage performance metrics and datasets directly from your IDE.
- MCP Resources and Resource Templates: Utilize metadata-aware flows for enhanced development.
This centralized access significantly improves productivity and consistency across your AI projects.
Links
- GitHub Repository: https://github.com/comet-ml/opik-mcp
- Website: https://www.comet.com/site/products/opik/?from=llm&utm_source=opik&utm_medium=github&utm_content=website_button&utm_campaign=opik
- Slack Community: https://chat.comet.com
- Twitter: https://x.com/Cometml
- Documentation: https://www.comet.com/docs/opik/?from=llm&utm_source=opik&utm_medium=github&utm_content=docs_button&utm_campaign=opik