A comprehensive Model Context Protocol (MCP) server that provides tools for interacting with Comet ML API. This server enables seamless integration with Comet ML's experiment tracking platform through a standardized protocol.

• 🔧 MCP Server: Full Model Context Protocol implementation for tool integration
• 📊 Experiment Management: List, search, and analyze experiments with detailed metrics
• 📁 Project Management: Organize and explore projects across workspaces
• 🔍 Advanced Search: Search experiments by name, description, and project
• 📈 Session Management: Singleton comet_ml.API() instance with robust error handling

• Python 3.8 or higher
• Comet ML account and API key

pip install comet-mcp --upgrade

The server uses standard comet_ml configuration:

1. Using comet init; or
2. Using environment variables

Example:

export COMET_API_KEY=your_comet_api_key_here

# Optional: Set default workspace (if not provided, uses your default)
export COMET_WORKSPACE=your_workspace_name

• list_experiments(workspace, project_name) - List recent experiments with optional filtering
• get_experiment_details(experiment_id) - Get comprehensive experiment information including metrics and parameters
• get_experiment_code(experiment_id) - Retrieve source code from experiments
• get_experiment_metric_data(experiment_ids, metric_names, x_axis) - Get metric data for multiple experiments
• get_default_workspace() - Get the default workspace name for the current user
• list_projects(workspace) - List all projects in a workspace
• list_project_experiments(project_name, workspace) - List experiments within a specific project
• count_project_experiments(project_name, workspace) - Count and analyze experiments in a project
• get_session_info() - Get current session status and connection information

• Structured Data: All tools return properly typed data structures
• Error Handling: Graceful handling of API failures and missing data
• Flexible Filtering: Filter by workspace, project, or search terms
• Rich Metadata: Includes timestamps, descriptions, and status information

Run the server to provide tools to MCP clients:

# Start the MCP server
comet-mcp

The server will:

• Initialize Comet ML session
• Register all available tools
• Listen for MCP client connections via stdio

Create a configuration for your AI system. For example:

{
  "servers": [
    {
      "name": "comet-mcp",
      "description": "Comet ML MCP server for experiment management",
      "command": "comet-mcp",
      "env": {
        "COMET_API_KEY": "${COMET_API_KEY}"
      }
    }
  ]
}

comet-mcp supports "stdio" and "sse" transport modes.

usage: comet-mcp [-h] [--transport {stdio,sse}] [--host HOST] [--port PORT]

Comet ML MCP Server

options:
  -h, --help            show this help message and exit
  --transport {stdio,sse}
                        Transport method to use (default: stdio)
  --host HOST           Host for SSE transport (default: localhost)
  --port PORT           Port for SSE transport (default: 8000)

For complete details on testing this (or any MCP server) see examples/README.

This project is licensed under the MIT License - see the LICENSE file for details.

• Documentation: GitHub Repository
• Issues: GitHub Issues
• Comet ML: Comet ML Documentation