The MCP-REPL server provides a comprehensive JavaScript/TypeScript execution and code analysis environment with advanced tooling for debugging, search, and transformation.
Execute JavaScript/TypeScript code directly with Node.js or Deno, supporting ESM imports, CommonJS compatibility, dynamic imports, type checking, and full access to native APIs including web requests
Debug and test hypotheses through iterative code execution with structured debugging approaches and batch operations for complex workflows
Perform semantic code search with natural language queries, metadata extraction, and AST-aware chunking across project directories with configurable folders, ignores, and extensions
Conduct AST-based pattern matching using ast-grep for searching, replacing, linting, and analyzing code structures with support for dry runs and interactive mode
Transform and validate code with pattern-based replacements and YAML-defined rule validation for linting purposes
Analyze AST structures with debugging capabilities for query analysis, pattern understanding, and full tree context viewing
Work across multiple environments including Claude Code, Cursor, GitHub Copilot, and VS Code with flexible configuration options
Provides a secure JavaScript REPL (Read-Eval-Print-Loop) environment to execute code snippets with error handling, memory management, and output formatting.
Enables secure access to Node.js built-in modules and execution of JavaScript code in a sandboxed VM context with working directory support.
Allows running the REPL directly via npx without installation or installing it globally through npm for repeated usage.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP-REPLexecute this JavaScript: console.log('Hello, World!');"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
gm-exec
Code execution tool for MCP clients and CLI. Multi-language support (JS/TS, Python, Go, Rust, C, C++, Deno, Java, bash). Built on Bun with PM2-managed process isolation.
MCP Server
Add to your MCP client config:
{
"mcpServers": {
"gm-exec": {
"command": "bunx",
"args": ["gm-exec", "--mcp"]
}
}
}Or install globally:
bun install -g gm-exec
gm-exec --mcpRelated MCP server: MCP QuickJS Runner
CLI
bunx gm-exec-cli exec --cwd=/app "console.log('hello')"
bunx gm-exec-cli bash --cwd=/app "npm install && npm test"
bunx gm-exec-cli exec --lang=python --cwd=/app "print('hello')"
bunx gm-exec-cli exec --file=script.jsCommands
gm-exec-cli exec [options] <code> Execute code (waits up to 15s, then backgrounds)
--lang=<lang> nodejs (default), python, go, rust, c, cpp, java, deno
--cwd=<dir> Working directory
--file=<path> Read code from file
gm-exec-cli bash [--cwd=<dir>] <cmd> Execute bash commands, same 15s ceiling
gm-exec-cli status <task_id> Poll status + drain output of a background task
gm-exec-cli close <task_id> Delete a background task
gm-exec-cli runner start Start the runner manually (PM2, no autorestart)
gm-exec-cli runner stop Stop the runner
gm-exec-cli runner status Show runner PM2 statusBackground execution
Commands have a hard 15-second ceiling. If still running after that, the process is backgrounded and you get a task ID with monitoring instructions:
Backgrounded after 15s — task still running.
Task ID: task_3
Watch output:
gm-exec-cli status task_3
gm-exec-cli close task_3
gm-exec-cli runner stopThe runner auto-starts before each command and auto-stops after — unless a task was backgrounded, in which case the runner stays alive until you explicitly stop it.
Supported Languages
Language | Runtime |
JavaScript / TypeScript | Node.js / Bun |
Python | python3 |
Go | go run |
Rust | rustc |
C | gcc |
C++ | g++ |
Java | javac + java |
Deno | deno run |
bash / sh / zsh | shell |
Requirements
Bun ≥ 1.0
curl -fsSL https://bun.sh/install | bashResources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.