Code Runner MCP

Let AI execute JavaScript/Python code with any package imports!

- Secure Sandbox: Isolated execution environment protecting your host system
- Install-on-Demand: Dynamically import any npm/PyPI packages
- Reduce Hallucinations: Let AI verify logic by executing code
- Quick Validation: Test if packages meet your needs without local installation

Agent Skill — skills.sh (Recommended for AI agents)

Install the bundled agent skill so your AI assistant knows how to usecode-runner-mcpout of the box:

npx skills add mcpc-tech/code-runner-mcp

This installs the skill into your project's.agent/skills/directory. Compatible with Claude Code, Cursor, Windsurf, GitHub Copilot, VS Code, andmore.

{ "mcpServers": { "code-runner": { "command": "deno", "args": ["run", "--allow-all", "jsr:@mcpc/code-runner-mcp/bin"], "env": { "DENO_PERMISSION_ARGS": "--allow-net", "NODEFS_ROOT": "/tmp", "NODEFS_MOUNT_POINT": "/tmp" }, "transportType": "stdio" } } }

{ "mcpServers": { "code-runner": { "command": "npx", "args": [ "-y", "deno", "run", "--allow-all", "npm:@mcpc-tech/code-runner-mcp@latest" ], "env": { "DENO_PERMISSION_ARGS": "--allow-net", "NODEFS_ROOT": "/tmp", "NODEFS_MOUNT_POINT": "/tmp" }, "transportType": "stdio" } } }

Note: Usesnpxto install and run Deno on demand — no separate Deno installation required.--experimental-wasm-stack-switchingcannot be passed viaNODE_OPTIONS(Node.js rejects it), but works as a direct CLI flag.

// Import npm packages directly to test functionality import { z } from "npm:zod"; import { serve } from "jsr:@std/http"; const schema = z.object({ name: z.string() }); console.log(schema.parse({ name: "test" }));

# Dynamically install and use Python packages import requests response = requests.get("https://api.github.com") print(f"Status code: {response.status_code}")

When import names differ from PyPI package names, use thepackagesparameter:

# sklearn -> scikit-learn, PIL -> Pillow from sklearn.datasets import load_iris data = load_iris() print(data.feature_names)

Usepackages: {"sklearn": "scikit-learn"}

# Access host file system (via NODEFS_ROOT and NODEFS_MOUNT_POINT) import os files = os.listdir('/tmp') # List files at the mount point print(f"Found {len(files)} files")

// Enable only Python { "ALLOWED_TOOLS": "python" } // Enable only JavaScript { "ALLOWED_TOOLS": "javascript" } // Enable both (default) { "ALLOWED_TOOLS": "python,javascript" }

- Deno Sandbox: Strict permission control with explicit authorization
- Pyodide WASM: WebAssembly isolated environment
- File System Isolation: Controlled host file access

- JavaScript/TypeScript: Powered byDenoruntime
- Python: Powered byPyodideWebAssembly technology
- Package Management: Dynamic installation from npm, JSR, and PyPI

Issues & Feedback:GitHub Issues
Repository:GitHub Repository

Execute any LLM-generated code in the YepCode secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages