vscode-mcp

MCP.Pizza Chef: block

The vscode-mcp client is a Model Context Protocol client designed to integrate AI agents and assistants like Goose or Claude with Visual Studio Code. It works alongside the vscode-mcp server and VSCode extension to enable real-time, structured interaction between LLMs and the VSCode environment, facilitating advanced AI-driven workflows within the IDE.

Use This MCP client To

Enable AI agents to interact with VSCode through MCP Integrate AI assistants like Goose or Claude into VSCode Facilitate real-time context sharing between VSCode and AI models Automate code editing and navigation using AI commands Enhance developer productivity with AI-driven code insights

README

VSCode MCP

This monorepo contains the VSCode MCP Server and its companion VSCode Extension, which together enable AI agents and assistants, like Goose or Claude, to interact with VSCode through the Model Context Protocol.

Project Structure

vscode-mcp/
├── server/    # MCP server implementation
└── extension/ # VS Code extension

Quick Start

  1. Install the MCP Server
npx vscode-mcp-server install
  1. Install the MCP Extension

MCP Extension

Configuration

Goose Desktop Setup

Goose Settings

  • ID: code-mcp
  • Name: VS Code
  • Description: Allows interaction with VS Code through the Model Context Protocol
  • Command: npx vscode-mcp-server

Claude Desktop Setup

Add this to your Claude Desktop config file (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "vscode-mcp-server": {
      "command": "npx",
      "args": ["vscode-mcp-server"],
      "env": {}
    }
  }
}

Available Tools

The Code MCP server provides the following tools for AI agents to interact with VS Code:

create_diff

Creates and shows a diff for modifying existing files:

  • Shows changes preview before applying
  • Requires user approval
  • Only works with existing files

open_file

Opens files in the VS Code editor:

  • Used for viewing new or modified files

open_project

Opens a project folder in VS Code:

  • Sets up working directory for AI agent

check_extension_status

Checks if extension is installed and responding

get_extension_port

Gets the port number for VS Code MCP Extension

list_available_projects

Shows projects from port registry file

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Copyright 2025 Block, Inc.

This product includes software developed at Block, Inc.

vscode-mcp FAQ

How do I install the vscode-mcp client?
Install the MCP server using 'npx vscode-mcp-server install' and add the VSCode MCP extension from the VSCode marketplace.
What AI assistants are compatible with vscode-mcp?
It supports AI agents like Goose and Claude, enabling them to interact with VSCode via MCP.
How does vscode-mcp improve VSCode workflows?
It allows AI models to access and manipulate VSCode context, enabling automated code edits, navigation, and insights.
Is vscode-mcp limited to a specific VSCode version?
It is designed to work with standard VSCode installations; ensure your VSCode is up to date for best compatibility.
Can I customize the AI interaction commands in vscode-mcp?
Yes, you can configure commands and settings to tailor AI interactions within VSCode.
Does vscode-mcp support multiple AI model providers?
Yes, it is provider-agnostic and works with models like OpenAI, Claude, and Gemini.
How secure is the interaction between AI agents and VSCode?
MCP enforces scoped and secure interactions, ensuring safe communication between AI models and the VSCode environment.