
JavaScript MCP Server
A server that enables AI assistants to execute JavaScript code with persistent context through stateful REPL sessions, file operations, and package management features.
README
JavaScript MCP Server (js-mcp)
A Model Context Protocol (MCP) server that allows AI assistants to execute JavaScript code with stateful REPL sessions.
Features
Core Features
- One-time JavaScript Execution: Execute JavaScript code directly in Node.js
- Stateful REPL Sessions: Maintain variables and context across multiple executions
- File System Operations: Read, write, and manipulate files
- Package Management: Import modules and manage npm packages
Advanced Features
- Secure sandboxed execution
- Asynchronous code support
- Error handling with formatted stack traces
- Session management with automatic cleanup
Installation
# Clone the repository
git clone https://github.com/yourusername/js-mcp.git
cd js-mcp
# Install dependencies
npm install
# Build the project
npm run build
Usage
Run with stdio transport (for use with Claude Desktop)
npm start
# or
node dist/index.js --stdio
Run with HTTP transport
node dist/index.js --http
# Default port is 3000, or specify with PORT environment variable
PORT=3456 node dist/index.js --http
Available Tools
JavaScript Execution
- execute_javascript: Run JavaScript code in a basic sandbox
- execute_javascript_with_modules: Run JavaScript with module imports
- execute_javascript_async: Run asynchronous JavaScript code
REPL Sessions
- repl_create_session: Create a new REPL session
- repl_execute: Execute code in a REPL session
- repl_get_context: Get variable values in a session
- repl_delete_session: Delete a session
- repl_list_sessions: List all active sessions
File Operations
- file_read: Read file contents
- file_write: Write content to a file
- file_list: List files in a directory
- file_delete: Delete a file or directory
- file_exists: Check if a file exists
Package Management
- package_check: Check if a module is available
- package_install: Install an npm package
- package_list: List installed packages
Security
The server uses direct JavaScript execution with safety features:
- Timeout limits for code execution
- File system access limited to working directory
- Path validation to prevent dangerous operations
Configuration
Configure the server by setting environment variables:
PORT
: HTTP server port (default: 3000)WORKING_DIRECTORY
: Base directory for file operations (default: current directory)SESSION_TIMEOUT
: REPL session timeout in minutes (default: 30)
Development
# Start in development mode
npm run dev
# Run tests
npm test
# Lint code
npm run lint
# Format code
npm run format
License
MIT
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.