112 published MCP servers in this category · page 1 of 2 · all categories
Code execution MCP servers let assistants run supported programs or notebook cells and retrieve their output. Some use a local runtime; others create an isolated hosted sandbox. They are useful when a task needs an actual computation rather than a proposed code snippet.
Compare supported languages, installed packages, time limits and filesystem persistence. Look at how standard output, errors and generated files are returned. A code runner does not necessarily provide a full desktop, network access or the same dependencies as your development environment.
Browse the servers below for available tools, connection options and links to the maintainer’s documentation. A server can belong to several categories when it supports several kinds of work.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
Runs Python code locally within an interactive REPL environment.
Executes Python code within ephemeral Daytona sandboxes, facilitating tasks such as code execution, file manipulation, and web server previewing.
Enables Claude to manage software development projects with project context awareness and code execution via Docker.
Give your agent a persistent workspace: files, a code sandbox and a public URL to publish to.
Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.
Open Models MCP for Blender Using Ollama
A Model Context Protocol server that provides browser automation capabilities using BrowserCat's cloud browser service. This server enables LLMs to interact with web pages, take screenshots, and…
TypeScript code execution API for Canvas MCP
🛡️ Undetectable browser MCP server — 66 tools, Patchright-powered, zero CDP fingerprint.
Chrome DevTools MCP Server for AI-assisted frontend development
MCP server for E2B code sandbox - Execute code and commands in secure E2B sandboxes
A secure Python code execution service designed to integrate with LLMs like GPT and Claude, providing a self-hosted alternative to OpenAI's Code
This bridge implements the "Code Execution with MCP" pattern, a convergence of ideas from industry leaders:
I do everything related to coding and execution tasks
Execute Python, JavaScript, or SQL in a sandbox. Get stdout, execution time, errors. 10s timeout. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.
A podman ubuntu 24.04 container that serves a MCP server; with file, code execution, bash shell, knowledgebase, and more.
Model Context Protocol (MCP) implementation for Jupyter notebooks to overcome limitation with Cursor
Model Context Protocol (MCP) server that lets MCP clients control and inspect DaVinci Resolve (including Fusion) through tools and resources.
Create and manage secure sandboxes for running AI agent code
If you need notebook/runtime tools, compose this server with `jupyter-mcp-server` using [mcp-compose](https://github.com/datalayer/mcp-compose).
Embody puts your ideas on screen as fast as you can describe them. Operators, connections, parameters, the works. Want to try a different direction?
⭐ If this is useful, please star the repo — it helps other agents & devs discover it.
Add to your MCP client and complete OAuth when prompted:
Your agent is auto-provisioned on first sign-in. There is **no** `register_agent` tool.
Disposable Firecracker microVM sandboxes for agents: run code, snapshot, fork. Needs Linux with KVM.
A zero-dependency MCP server that gives coding agents read and write access to a live Figma canvas, then closes the loop by handing the rendered PNG back to the model for visual self-critique.
Bounded readonly SHA256 verification with the official MCP SDK. No code execution or model calls.
Run Python in a code sandbox.
A server to interact with FreeCAD models using the Model Context Protocol (MCP).
A Model Context Protocol (MCP) server that enables AI assistants to interact with FreeCAD for 3D modeling and CAD operations.
An MCP (Model Context Protocol) server that enables integration between AI assistants (Claude, GPT, and other MCP-compatible tools) and FreeCAD, allowing AI-assisted development and debugging of 3D…
Runbox MCP provides remote coding environment for AI and agents. It can publish your AI-written website code as real world URL domain. Deploy your AI generated code as a real website running in…
MCP is powerful. Enterprise MCP deployment is a different problem entirely.
MCP server for Google Apps Script: CommonJS module system, ad-hoc code execution, Unix-inspired commands (cat, grep, ls), and AI-assisted development
MCP (model context protocol) server for running python code.
Model Context Protocol (MCP) server for HOPX. Enables AI assistants to execute code in isolated cloud containers.
MCP server for 1C:Enterprise (ERP, Accounting, etc.) — 51 tools for metadata, documents, registers, reports and more
An MCP server for sandboxed Python code execution with IPython and Docker, and file transfer.
MCP server providing secure code execution (Python, Go, JS) via containers.
Compatible with any Jupyter deployment (local, JupyterHub, ...) and with [Datalayer](https://datalayer.ai) hosted Notebooks.
A JupyterLab extension to manage MCP servers.
🌍 Jupyter Earth MCP Server is a [Model Context Protocol](https://modelcontextprotocol.io) (MCP) server implementation that provides a set of tools
JupyterMCP connects Jupyter Notebook to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Jupyter Notebooks. This integration enables…
Jupyter Notebook 是数据科学家最常用的工具之一，它提供了一个交互式的环境，使其可以方便地进行数据分析、可视化、机器学习等探索性任务。然而，由于Notebook自身的格式限制，使得其难以像纯文本文件（如Markdown、Python文件）一样被AI直接理解。
A comprehensive Model Context Protocol (MCP) server that bridges AI agents with Jupyter notebooks, enabling real-time code execution, visualization generation, and advanced image extraction…
JupyterMCP connects Jupyter Notebook to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Jupyter Notebooks. This integration enables…
An implementation of the Model Context Protocol (MCP) server that enables interaction with Jupyter notebooks running in any JupyterLab environment, including local instances. Designed for seamless…
A FastMCP server that provides tools for interacting with Jupyter notebooks. Built using the [FastMCP framework](https://github.com/jlowin/fastmcp).
Jupythunder is a middleware that connects the LLM chat interface (Claude) with Jupyter Notebook. This project allows users to interact with Jupyter Notebook in a way that's closer to natural language.
The LeetCode MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with LeetCode APIs, enabling advanced automation and intelligent interaction with LeetCode's…
A Model Context Protocol (MCP) server implementation that can browse the web, perform search queries, and execute code.
MCP server for Jupyter notebooks
A production-grade MCP server providing a persistent Python REPL with multi-session support, sandboxing, and timeout protection.
MCP server for Python code execution and environment management
基于Playwright的模型上下文协议(MCP)服务器，为AI助手提供强大的浏览器自动化能力
Unified MCP server bridging Claude Code and Ollama to Roblox Studio and Blender.
Fetch web pages using Chrome/Edge browser with auth, anti-bot, and JavaScript rendering support
execute code
An extensible Message Communication Protocol (MCP) server that provides secure code execution capabilities in isolated sandbox environments. This