VSCode Context MCP
A Model Context Protocol (MCP) server that provides VSCode context and filesystem operations for AI assistants.
README
VSCode Context MCP
A Model Context Protocol (MCP) server that provides VSCode context and filesystem operations for AI assistants.
Overview
VSCode Context MCP creates a bridge between AI assistants and your VSCode environment. It enables AI models to:
- Access the current VSCode context (active files, tabs, terminal output)
- Perform filesystem operations with controls
- Execute shell commands in a controlled environment
This allows AI assistants to provide more relevant and context-aware help for software development tasks.
Features
VSCode Context Access
- Get current project path
- Retrieve active file contents and metadata
- List open editor tabs
- Access diagnostic problems (warnings/errors)
- Retrieve terminal output
- Access files attached to the workspace
Filesystem Operations
- Read/write files
- Edit files with line-based changes
- Create directories
- List directory contents
- Generate directory trees
- Search for files
- Get file metadata
- Move/rename files
Command Execution
- Run shell commands with output capture
- Controlled execution environment
⚠️ Security Warning
Be careful what you ask this server to run! In the Claude Desktop app, use Approve Once (not Allow for This Chat) so you can review each command, and use Deny if you don't trust the command. Permissions are dictated by the user running the server.
This tool does not yet implement comprehensive security measures, so treat it with caution.
Integration with AI Assistants
This MCP server is designed to work with Model Context Protocol-compatible AI assistants. It enhances their ability to:
- Understand your code context
- Make informed suggestions
- Provide relevant examples
- Help debug issues
- Perform file operations on your behalf
1. Install the VSCode Extension
Note: Before installation, it's recommended to uninstall similar MCP servers such as filesystem MCP to avoid conflicts.
- Download the VSIX package from here
- Open VSCode
- Press
Ctrl+Shift+P(Windows/Linux) orCmd+Shift+P(macOS) to open the command palette - Type "Extensions: Install from VSIX..." and select it
- Navigate to the downloaded VSIX file and select it
- Restart VSCode after installation
For more information, visit the VSCode extension repository
2. Set Up and Run the MCP Server
First, clone or download this repository. Then, install the dependencies and build the project:
cd path/to/vscode-context-mcp
npm install
npm run build
Once built, update your Claude Desktop configuration to use the MCP server:
{
"mcpServers": {
"vscode-context-mpc": {
"command": "node",
"args": [
"C:\\path\\to\\vscode-context-mcp\\dist\\index.js"
]
}
}
}
Note: Make sure the file path in the
argsarray matches your actual project location.
3. Test the Connection
To verify that everything is working correctly, try using this prompt in Claude:
Please check my current VSCode project and tell me what files I have open.
4. Add Files to Claude Context
You can add files to your Claude context in a few ways:
- Press
Ctrl+L(Windows/Linux) orCmd+L(macOS) to add the current file - Press
Ctrl+IorCmd+Ito add only the selected text - Open the command palette (
Ctrl+Shift+PorCmd+Shift+P) and search for:- "Add File to Context"
- "Add Selection to Context"
Tool Reference
| Tool Name | Description |
|---|---|
get_vscode_context |
Retrieve complete VSCode context information |
get_attached_files |
Retrieve a list of files attached to the workspace |
get_project_path |
Get current project root directory |
get_current_file |
Get details and content of the active file |
get_open_tabs |
List all open editor tabs |
get_problems |
Retrieve diagnostics (errors/warnings) |
get_terminal_content |
Get terminal output and history |
run_command |
Execute a shell command |
read_file |
Read contents of a file |
read_multiple_files |
Read multiple files at once |
write_file |
Create or overwrite a file |
edit_file |
Make line-based edits to a file |
create_directory |
Create directory structure |
list_directory |
List files and directories |
directory_tree |
Get recursive directory structure |
move_file |
Move or rename files and directories |
search_files |
Find files matching a pattern |
get_file_info |
Get detailed file metadata |
Roadmap
- Make support for multiple VSCode projects
- Accept/Revert functionality when writing or editing files
- Redesign UI
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License – see the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.