Tabby
MCP server for Tabby terminal, 34 MCP tools including SFTP support, full control your Tabby!
claude mcp add --transport stdio gentlemanhu-tabby-mcp node dist/server.js \ --env ENV="Optional environment variable for future customization"
How to use
Tabby-MCP exposes a comprehensive set of tools that integrate Tabby Terminal with AI-driven workflows. Once the server is running, you can call a suite of terminal control, tab management, profile/SSH, and SFTP operations via the MCP protocol. The available tools include commands to execute shell commands with output capture, manage multiple terminal tabs and panes, open profiles or SSH connections, and perform remote file operations through SFTP (requires the tabby-ssh plugin). The server supports stable session identifiers and flexible targeting for commands, enabling AI agents to operate across sessions, tabs, and profiles securely. When using the STDIO or HTTP stream modes, clients will connect to the MCP endpoint and issue the appropriate tool calls with their parameters to orchestrate terminal actions on your machine.
How to install
Prerequisites:
- Node.js 18+ installed on the host (for building or running the server in Node mode).
- Git installed to clone the repository.
Installation steps:
-
Clone the repository: git clone https://github.com/GentlemanHu/Tabby-MCP.git cd Tabby-MCP
-
Install dependencies and build (recommended): npm install --legacy-peer-deps npm run build
Copy the built dist/ and package.json to your Tabby plugins folder as instructed by the build script
-
Alternative: Quick install script (pre-built binaries, no Node.js required): curl -fsSL https://raw.githubusercontent.com/GentlemanHu/Tabby-MCP/main/scripts/install.sh | bash
Or use the Windows PowerShell installer provided in the repository
-
Start the MCP server:
If you built locally:
node dist/server.js
Or use the provided startup script if available in your environment
-
After the server starts, open Tabby → Settings → MCP and start the MCP server from the UI.
Additional notes
Notes and tips:
- STDIO mode requires Node.js if you’re using the JSON bridge in IDEs like Claude or VS Code.
- The server exposes multiple endpoints for HTTP stream mode and a legacy SSE mode. Use the Streamable HTTP endpoint for robust real-time streaming.
- SFTP operations require the tabby-ssh plugin to be installed in Tabby; otherwise, SFTP tools are disabled automatically.
- The tools support flexible session targeting (sessionId, tabIndex, title, profileName). If no target is specified, the active session is used by default.
- If you plan to run the server behind a firewall or NAT, ensure the chosen port (default 3001) is accessible to clients. Update endpoints accordingly in your mcp.json configuration if you customize ports.
- For debugging, consult the health and info endpoints to verify the server state and version.
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
mcp-google-map
A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.