Skip to content
Back to search

tabby-vscode-agent

MCP server for control Tabby terminal

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/steffmet--tabby-vscode-agent/badge.svg)](/listings/steffmet--tabby-vscode-agent)

HTML

<a href="/listings/steffmet--tabby-vscode-agent"><img src="/api/listings/steffmet--tabby-vscode-agent/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Ensure the plugin is installed using one of the methods above. 2. Launch Tabby and go to **Settings → Copilot**. 3. Within the settings page, you'll find a collapsible **"Instructions"** section. This provides detailed, step-by-step guidance on how to integrate the agent with VS Code. 4. Configure the MCP server port (default: `3001`). 5. Toggle "Start on Boot" if you wish for the server to automatically launch with Tabby. 6. Connect your preferred AI client to the MCP server. A list of supported clients can be found at [https://modelcontextprotocol.io/clients](https://modelcontextprotocol.io/clients).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 195 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # 🚀 Tabby VSCode Agent
  2. > The Tabby VSCode Agent is an advanced plugin for [Tabby Terminal](https://github.com/Eugeny/tabby), designed to seamlessly integrate AI-powered terminal control and automation directly within VS Code. Building upon the foundations of the original [Tabby MCP Server](https://github.com/thuanpham582002/tabby-mcp-server), this improved version offers enhanced functionality, quicker speeds, and a more refined user experience tailored for VS Code users.
  3. ## 🆕 What's New in 1.0.8 (21-07-2025)
  4. ### Added
  5. - VSCode Extension Support, listens to http port.
  6. - Fixed URL Opening links
  7. - Increased speed of reading SSH sessions
  8. - Fixed issue with opening VSCode via non extension
  9. - Fixed UI for Command History
  10. - Enhanced support for VS Code integration
  11. - Added support for VSCode Extension
  12. - Copilot agent chat can now be opened directly from the navbar
  13. - New and improved UI elements for a more modern look
  14. - Updated and fixed navbar for better navigation and stability
  15. - Improved command execution speeds and responsiveness
  16. - Quick access to settings and chat from the main interface
  17. - More robust error handling and feedback for users
  18. - Optimized MCP server communication for lower latency
  19. - Improved hotkey support and customization
  20. - Better handling of long-running commands and output
  21. ### Fixed
  22. - Navbar rendering issues in some VS Code versions
  23. - UI glitches in command dialogs and modals
  24. - Minor bugs in command history and output storage
  25. - Various performance and stability improvements
  26. ## 📹 Video Demonstrations
  27. Witness the Tabby VSCode Agent in action with these comprehensive video demonstrations:
  28. ### VSCode Agent in Action
  29. [![Tabby VSCode Agent Demo](assets/gifs/vscodeagent.gif)](assets/gifs/vscodeagent.gif)
  30. ### Tabby Settings Overview
  31. [![Tabby Settings Demo](assets/gifs/tabbysettings.gif)](assets/gifs/tabbysettings.gif)
  32. ## ✨ Key Features
  33. - 🤖 **AI Integration**: Effortlessly connect AI assistants to your terminal for intelligent command execution and automation.
  34. - 🔌 **Built-in MCP Server**: Features a robust Model Context Protocol (MCP) server implementation for reliable communication.
  35. - 🚀 **Deep VS Code Integration**:
  36. - **Open Chat from Navbar**: Instantly open the Copilot chat window directly from the Tabby navigation bar within VS Code.
  37. - **Optimised Settings & Logins**: Enjoy a redesigned settings interface and streamlined login processes for a smoother workflow.
  38. - **Enhanced Speed**: Experience significantly quicker response times and overall performance.
  39. - 📦 **Bundled Stdio Server**: Includes `tabby-mcp-stdio` for a stable and efficient connection with VS Code.
  40. - 🖥️ **Terminal Control**: Empower AI to execute commands, read terminal output, and manage your sessions.
  41. - 🔍 **Session Management**: View and manage your SSH sessions directly from the plugin.
  42. - 🚫 **Command Abort**: Safely abort any running commands with ease.
  43. - 📋 **Buffer Access**: Retrieve terminal buffer content with flexible line range options.
  44. - 🔒 **Pair Programming Mode**: An optional safety feature that requires confirmation before AI executes commands, ensuring you maintain control.
  45. - 📊 **Command History**: Keep track of and review all previously executed commands.
  46. - 🔄 **Command Output Storage**: Access complete command outputs with convenient pagination.
  47. ## 🔧 Installation
  48. ### Install from Tabby Plugin Store
  49. 1. Open Tabby settings and navigate to **Plugins → MCP**.
  50. 2. Locate and click "Install" on the **Tabby VSCode Agent** plugin.
  51. 3. Restart Tabby to finalise the installation.
  52. 4. Proceed to configure VS Code with the MCP Server as detailed below.
  53. ## 🚀 Quick Start
  54. 1. Ensure the plugin is installed using one of the methods above.
  55. 2. Launch Tabby and go to **Settings → Copilot**.
  56. 3. Within the settings page, you'll find a collapsible **"Instructions"** section. This provides detailed, step-by-step guidance on how to integrate the agent with VS Code.
  57. 4. Configure the MCP server port (default: `3001`).
  58. 5. Toggle "Start on Boot" if you wish for the server to automatically launch with Tabby.
  59. 6. Connect your preferred AI client to the MCP server. A list of supported clients can be found at [https://modelcontextprotocol.io/clients](https://modelcontextprotocol.io/clients).
  60. ## 💻 Usage Examples
  61. ### Connecting an AI to Control Your Terminal
  62. 1. Start Tabby with the Tabby VSCode Agent plugin enabled.
  63. 2. Configure your AI client to connect to the MCP server (refer to [Connecting to MCP](#-connecting-to-mcp) for details).
  64. 3. Instruct your AI assistant to run commands or manage your terminal sessions.
  65. Example AI prompt:
  66. ```
  67. Connect to my Tabby VSCode Agent and list all available terminal sessions.
  68. Then execute the command "ls -la" in the first available terminal.
  69. ```
  70. ## 🔗 Connecting to MCP
  71. ### HTTP Server (Recommended for most clients)
  72. To configure AI clients to use your MCP server, add the following to your `mcp.json` file:
  73. ```json
  74. {
  75. "servers": {
  76. "tabby": {
  77. "url": "http://localhost:3001/sse",
  78. "type": "http"
  79. }
  80. }
  81. }
  82. ```
  83. ### Stdio Server (for VS Code)
  84. For a more robust integration with VS Code, you can utilise the bundled `stdio` server.
  85. 1. Navigate to **Settings → Copilot** in Tabby.
  86. 2. Under the **Stdio Server** section, you will find the full path to the server script.
  87. 3. Click the "Copy" button to copy the path to your clipboard.
  88. 4. In your VS Code `mcp.json`, configure the server as shown below, pasting the copied path:
  89. ```json
  90. {
  91. "servers": {
  92. "tabby-stdio": {
  93. "type": "stdio",
  94. "command": "node",
  95. "args": ["<PASTE THE COPIED PATH HERE>"]
  96. }
  97. }
  98. }
  99. ```
  100. ### Pair Programming Mode
  101. The plugin includes a "Pair Programming Mode" to enhance safety when AI assistants control your terminal:
  102. - **Confirmation Dialogue**: Prompts the user for confirmation before executing commands.
  103. - **Auto Focus Terminal**: Automatically focuses the terminal when commands are executed.
  104. - **Command Rejection**: Provides the ability to reject commands with feedback.
  105. To enable Pair Programming Mode:
  106. 1. Go to Tabby settings → Copilot.
  107. 2. Toggle "Enable Pair Programming Mode".
  108. 3. Configure additional safety options as required.
  109. ## 📚 API Reference
  110. ### Available Tools
  111. | Tool | Description | Parameters |
  112. |------|-------------|------------|
  113. | `open-vscode-chat` | Opens the VSCode chat window. | None |
  114. | `get_ssh_session_list` | Get list of all terminal sessions | None |
  115. | `exec_command` | Execute a command in terminal | `command`, `tabId`, `commandExplanation` |
  116. | `get_terminal_buffer` | Get terminal content | `tabId`, `startLine`, `endLine` |
  117. | `get_command_output` | Retrieve complete command output | `outputId`, `startLine`, `maxLines` |
  118. ## 🤝 Contributing
  119. Contributions are highly encouraged! Here's how you can contribute to the Tabby VSCode Agent:
  120. 1. Fork the repository.
  121. 2. Create a new feature branch (`git checkout -b feature/your-feature`).
  122. 3. Commit your changes (`git commit -m 'Add your feature'`).
  123. 4. Push your branch to the origin (`git push origin feature/your-feature`).
  124. 5. Open a Pull Request.
  125. Please refer to the [contributing guidelines](CONTRIBUTING.md) for more detailed information.
  126. ### Development Workflow
  127. 1. Clone the repository and install dependencies:
  128. ```bash
  129. git clone https://github.com/SteffMet/tabby-vscode-agent.git
  130. cd tabby-vscode-agent
  131. npm install
  132. ```
  133. 2. Make your desired changes to the codebase.
  134. 3. Build the plugin:
  135. ```bash
  136. npm run build
  137. ```
  138. 4. Test the plugin with Tabby:
  139. ```bash
  140. npm run deploy
  141. ```
  142. ## 📝 Licence
  143. This project is licensed under the MIT Licence - see the [LICENCE](LICENCE) file for details.
  144. ---
  145. <p align="center">
  146. Made with ❤️ by <a href="https://github.com/SteffMet">SteffMet</a>
  147. </p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.