Top Code Execution MCP Servers - Ranked by GitHub Stars

9 of 9 servers

pydantic/pydantic-ai/mcp-run-python

14.0k

Run Python code in a secure sandbox via MCP tool calls

github.com/pydantic/pydantic-ai/tree/main/mcp-run-python

dagger/container-use

3.4k

Containerized environments for coding agents. Multiple agents can work independently, isolated in fresh containers and git branches. No conflicts, many experiments. Full execution history, terminal access to agent environments, git workflow. Any agent/model/infra stack.

github.com/dagger/container-use

ckanthony/openapi-mcp

164

OpenAPI-MCP: Dockerized MCP Server to allow your AI agent to access any API with existing api docs.

github.com/ckanthony/openapi-mcp

alfonsograziano/node-code-sandbox-mcp

141

A Node.js MCP server that spins up isolated Docker-based sandboxes for executing JavaScript snippets with on-the-fly npm dependency installation and clean teardown

github.com/alfonsograziano/node-code-sandbox-mcp

yepcode/mcp-server-js

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

github.com/yepcode/mcp-server-js

gwbischof/outsource-mcp

Give your AI assistant its own AI assistants. For example: "Could you ask openai to generate an image of a dog?"

github.com/gwbischof/outsource-mcp

ouvreboite/openapi-to-mcp

Lightweight MCP server to access any API using their OpenAPI specification. Supports OAuth2 and full JSON schema parameters and request body.

github.com/ouvreboite/openapi-to-mcp

r33drichards/mcp-js

🦀 🏠 🐧 🍎 - A Javascript code execution sandbox that uses v8 to isolate code to run AI generated javascript locally without fear. Supports heap snapshotting for persistent sessions.

github.com/r33drichards/mcp-js

hileamlakB/PRIMS

A Python Runtime Interpreter MCP Server that executes user-submitted code in an isolated environment.

github.com/hileamlakB/PRIMS