VSCode MCP: Real-Time Collaboration & DevOps Mastery

VSCode MCP: The MCP server & extension duo devs crave—code smarter, collab real-time, and crush dev ops. Effortless, powerful, and built for speed." )

Visit Repository

✨ Developer Tools

4.6(48 reviews)

72 saves

33 comments

This tool saved users approximately 9600 hours last month!

About VSCode MCP

What is VSCode MCP: Real-Time Collaboration & DevOps Mastery?

VSCode MCP (Model Context Protocol) is a monorepo solution enabling AI agents like Goose or Claude to interact with VS Code via a standardized protocol. Comprising a server and extension, it facilitates real-time collaboration between developers and AI models, streamlining DevOps workflows through dynamic file manipulation and environment integration.

How to use VSCode MCP: Real-Time Collaboration & DevOps Mastery?

Deploy the Server: Run npx vscode-mcp-server install to set up the backend infrastructure.
Activate the Extension: Install the MCP Extension from the VS Code Marketplace.
Configure AI Agents:
- Goose: Define code-mcp in settings with the specified command.
- Claude: Append MCP server details to claude_desktop_config.json as shown in the original documentation.

VSCode MCP Features

Key Features of VSCode MCP: Real-Time Collaboration & DevOps Mastery?

Empower AI-driven workflows with:

Interactive Diff Previews: The create_diff tool displays file modifications before execution, requiring explicit user validation.
Contextual Project Management: open_project establishes workspace boundaries, while list_available_projects tracks active environments.
Environment Diagnostics: check_extension_status and get_extension_port ensure seamless connectivity diagnostics.

Use Cases of VSCode MCP: Real-Time Collaboration & DevOps Mastery?

Optimize workflows through:

Remote Pair Programming: Enable AI models to suggest edits while maintaining human oversight via diff approvals.
Automated Deployment Pipelines: Integrate with DevOps toolchains using pre-approved file modifications.
Dynamic Documentation: Generate and validate code comments or markdown files through AI-driven open_file interactions.

VSCode MCP FAQ

FAQ from VSCode MCP: Real-Time Collaboration & DevOps Mastery?

How do I troubleshoot connection issues?: Verify port availability using get_extension_port and ensure firewall rules permit communication between AI agents and the MCP server.
Can I customize the diff approval flow?: Currently, the approval mechanism is hardcoded for security, but configuration options may be introduced in future iterations.
What security measures are implemented?: All file operations require explicit user consent, and commands are sandboxed through the VS Code extension host environment.

Content

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

Install the MCP Server

npx vscode-mcp-server install

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.

This product includes software developed at Block, Inc.