What is Tabby Mcp Server

Tabby-MCP-Server is a powerful plugin that implements the Model Context Protocol (MCP) for AI terminal control and automation.

Use cases

Use cases include automating command execution, managing SSH sessions with AI assistance, and retrieving terminal output for analysis or logging.

How to use

To use Tabby-MCP-Server, clone the repository, build the Docker image, and run the container. Follow the installation instructions provided in the README.

Key features

Key features include AI connection for seamless integration with terminal, built-in MCP server, terminal control for executing commands, session management for SSH sessions, command abort functionality, and flexible buffer access.

Where to use

Tabby-MCP-Server can be used in various fields such as software development, system administration, and automation tasks where AI can enhance terminal interactions.

🚀 Tabby-MCP-Server

Powerful Tabby plugin that implements Model Context Protocol (MCP) server, enabling AI-powered terminal control and automation.

📹 Video Demo

Watch the full video demonstration of Tabby-MCP in action:

✨ Features

• 🤖 AI Connection: Seamlessly connect AI assistants to your terminal
• 🔌 MCP Server: Built-in Model Context Protocol server implementation
• 🖥️ Terminal Control: Allow AI to execute commands and read terminal output
• 🔍 Session Management: View and manage SSH sessions
• 🚫 Command Abort: Safely abort running commands
• 📋 Buffer Access: Retrieve terminal buffer content with flexible options

📋 Table of Contents

• Installation
• Quick Start
• Usage Examples
• Configuration
• API Reference
• Contributing
  • Continuous Integration
• License

🔧 Installation

Using Docker

You can build and install the plugin using Docker with the following command:

git clone https://github.com/thuanpham582002/tabby-mcp-server.git
cd tabby-mcp-server
# Build the Docker image
docker build -t tabby-mcp . && docker run -v $(pwd)/build:/output tabby-mcp
bash scripts/copy_to_plugin_folder.sh

This command builds a Docker image tagged as ‘tabby-mcp’ and runs a container from this image, mounting your local ‘build’ directory to ‘/output’ in the container. The script scripts/copy_to_plugin_folder.sh will copy the built files to the Tabby plugin folder.

Note: Our CI/CD workflows on GitHub also use this Docker-based build process to ensure consistency between local development and production releases.

🚀 Quick Start

1. Install the plugin
2. Configure your Tabby environment
3. Connect to MCP server from any of the supported clients listed at https://modelcontextprotocol.io/clients

💻 Usage Examples

Connect an AI to Control Your Terminal

Retrieve SSH Session List

⚙️ Configuration

Configure the MCP server through the Tabby settings:

MCP Client Configuration

When connecting to the Tabby MCP server from an AI client (like Claude, GPT, etc.), use the following configuration:

{
  "mcpServers": {
    "Tabby MCP": {
      "url": "http://localhost:3001/sse"
    }
  }
}

You may need to adjust the url parameter if you’ve configured a different host or port in your server settings.

📚 API Reference

Available Tools

🤝 Contributing

Contributions are welcome! Here’s how you can help:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

See the contributing guidelines for more details.

Continuous Integration

Our project uses GitHub Actions for CI/CD with Docker-based builds:

• Pull Requests: Automatically built and tested using Docker to ensure compatibility
• Main Branch: Builds with Docker, publishes to npm, and creates GitHub releases
• Benefits: Consistent environment across development, testing, and production

To set up the CI/CD pipeline in your fork:

1. Configure the required secrets in your repository settings:

   • NPM_TOKEN: Your npm access token for publishing
   • GITHUB_TOKEN: Automatically provided by GitHub Actions

2. The workflows will automatically run on push and pull request events.

📝 License

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

Made with ❤️ by Pham Tien Thuan