Colab MCP

🚀 Colab MCP 🔗

Stop losing context when you switch between AI coding tools.

Colab MCP is a Model Context Protocol (MCP) server that enables Claude Code, Cursor, Codex, and other AI coding assistants to share logs and session history with each other.

📌 The Problem

When you're coding with Claude Code and make some progress, then switch to Cursor to test something, you'll lose all your context. You have to explain everything again. And if you jump to Codex next, you'll have to explain it all over again.

It's really exhausting.

💡 The Solution

Colab MCP is a shared MCP server that exposes your chat logs, terminal history, and IDE events as tools and resources across all your AI coding assistants.

When you switch tools, your AI already knows what you were working on. No more copy - pasting. No more re - explaining. Just a continuous workflow.

✨ Features

• 🔄 Share context across tools - Works with Claude Code, Cursor, Codex, Gemini.
• 📜 Access chat transcripts from previous sessions.
• 🔍 Search across all logs - Find that conversation from last week.
• 🎯 Session summaries - Get a quick overview of what you were working on.
• 🖥️ Terminal & IDE event tracking - See what commands were run.
• 🚀 Fast setup - One command to install across all your tools.

🚀 Quick Start

1. Install

pip install colab-mcp

2. Configure Your AI Tools

Run the interactive installer:

sudo colab-mcp-install

The installer will:

• 🔍 Detect which AI coding tools you have installed.
• ✅ Let you choose which ones to configure.
• ⚙️ Add Colab MCP to their MCP server configs.
• 📝 Give you instructions to restart each tool.

3. Restart Your AI Tools

Restart Claude Code, Cursor, Codex, or whichever tools you configured.

That's it! 🎉

📖 Usage

Once installed, Colab MCP exposes several tools and resources to your AI assistants:

Tools

• list_sessions - Get a list of all coding sessions.
• fetch_transcript - Retrieve the full transcript of a session.
• summarize_session - Get a quick summary of what happened.
• search_logs - Search across all logs (chat, MCP, IDE events).
• codex_status - Check recent Codex CLI activity.

Example Prompts

Try asking your AI assistant:

"What was I working on in my last session?" "Search my logs for discussions about authentication" "Summarize my session from yesterday afternoon" "What errors did I encounter in the last hour?"

🛠️ Manual Configuration

If you prefer to configure manually, add this to your MCP config:

Claude Code (~/.claude/mcp.json)

{
  "servers": {
    "colab-mcp": {
      "command": "colab-mcp",
      "env": {
        "CLAUDE_HOME": "/home/yourusername/.claude",
        "CURSOR_LOGS": "/home/yourusername/.cursor-server/data/logs",
        "TMPDIR": "/tmp"
      }
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "colab-mcp": {
      "command": "colab-mcp",
      "env": {
        "CLAUDE_HOME": "/home/yourusername/.claude",
        "CURSOR_LOGS": "/home/yourusername/.cursor-server/data/logs",
        "TMPDIR": "/tmp"
      }
    }
  }
}

Codex (~/.codex/config.toml)

[mcp_servers.colab-mcp]
command = "colab-mcp"
args = []
env = { CLAUDE_HOME = "/home/yourusername/.claude", CURSOR_LOGS = "/home/yourusername/.cursor-server/data/logs", TMPDIR = "/tmp" }

🗂️ Architecture

graph TB
    subgraph AI["AI Tools"]
        Claude[Claude Code]
        Cursor[Cursor]
        Codex[Codex]
    end
    
    MCP[Colab MCP Server]
    
    subgraph Logs["Log Files"]
        Chat[Chat History]
        IDE[IDE Events]
        Term[Terminal]
    end
    
    Claude --> MCP
    Cursor --> MCP
    Codex --> MCP
    
    MCP --> Chat
    MCP --> IDE
    MCP --> Term
    
    style MCP fill:#e8f4f8,stroke:#4a90a4,stroke-width:2px
    style AI fill:#f9f9f9,stroke:#ccc
    style Logs fill:#f9f9f9,stroke:#ccc

🤝 Contributing

Contributions are welcome! Check out the docs/ folder for more detailed information about how Colab MCP works.

📝 License

MIT License - see LICENSE for details.

🙏 Acknowledgments

Built with FastMCP - the fastest way to build MCP servers in Python.

Made with ❤️ by developers tired of losing context