Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.

This is a server that implements the MCP code execution mode. Through a single-tool bridge and zero-context discovery mechanism, it reduces the overhead of MCP tool calls from tens of thousands of tokens to about 200 tokens and securely executes Python code in the root container, supporting data science and secure isolation.

A secure code sandbox environment based on Docker containers, providing an isolated execution space for AI applications.

The Code Runner MCP Server is an MCP service that supports the execution of multi - language code snippets. It can directly run code and display results in applications such as VS Code.

A secure Docker container code sandbox environment that provides an isolated execution space for AI applications, supporting multiple programming environments and file operations.

This project implements functions similar to Claude Code through the MCP protocol, providing tools for code understanding, modification, and command execution. It supports multiple models and Jupyter notebook operations, and has security control and development expansion capabilities.

Claude code editing and execution service implemented based on the MCP protocol

The MCP Front - end Testing Server provides functions such as code analysis, test generation and execution, and React component testing, and supports the Jest and Cypress frameworks.

A Docker-based secure code execution environment that provides isolated sandbox support for the MCP protocol

JupyterMCP is a tool that integrates Jupyter Notebook with Claude AI via the Model Context Protocol (MCP). It supports functions such as bidirectional communication, cell operations, and code execution, and is only compatible with Jupyter Notebook version 6.x.

An MCP server that provides an isolated Docker environment, supporting code execution, package installation, and environment configuration in multiple programming languages

The VibeCheck Web testing tool is an AI-driven web testing agent designed to simplify the web testing process for developers. It integrates with AI programming assistants through the MCP protocol, supporting automated test recording, execution, and discovery, and helping developers quickly identify and fix code issues.

The Xray MCP Server is a tool that integrates the Xray Cloud API with MCP clients such as Claude Code. It provides functions such as test case management, test execution, test planning, and test set grouping, and supports CI/CD integration and test automation.

The ValTown MCP Server is a service designed for AI assistants, allowing code execution in the ValTown environment, supporting multiple platforms and being compatible with mainstream MCP clients.

The Go Playground MCP server is a tool integrated with the Go Playground API that can execute Go code and generate shareable URL links through the MCP protocol

This project is a multi - tool integration and code execution platform based on FastMCP. It supports importing MCP tools from local and SSE clients, provides Docker deployment and streaming code execution management, and is suitable for various tool invocation scenarios such as chemical information query and web page parsing.

Nash MCP is a multi - functional command execution server that supports Shell command execution, Python code execution, web content fetching, and task management, providing secure credential storage and session management functions.

Riza provides a secure code interpreter service, offering an isolated execution environment for LLM-generated code through the MCP server.

The MCP service for Emacs, supporting the generation and execution of Elisp code

CodeBox-AI is a secure Python code execution service that provides self-hosted code interpreter functionality, supports conversational code execution, dynamic package installation, and visual output, and integrates the MCP protocol for interaction with LLM applications.

OneTool is a unified MCP server that exposes over 100 tools through the Python API, significantly reducing token consumption and cost when AI calls tools, avoiding context pollution, and supporting multiple functions such as web search, database, file operations, and chart drawing.

The Roo Activity Logger is an MCP server used to automatically record the activities of Roo Code (Cline), including command execution, code generation, etc., and saves the logs as JSON files for subsequent search and analysis.

An MCP server that connects an LLM to the Roblox game client, supporting code execution, script inspection, remote call monitoring, screenshot taking, etc. in the game, and supporting multi-client connection and primary-secondary mode.

The YepCode MCP Server is a server implementing the Model Context Protocol. It can transform YepCode processes into AI tools, supports remote and local deployment, and provides functions such as code execution, environment management, and process execution.

An AI planning system integrating Google Gemini CLI and Claude Code, providing functions such as automatic planning and execution, persistent context management, and MCP integration.

Desktop Commander MCP is a server tool designed for the Claude desktop application, supporting terminal command execution, file system operations, and code editing functions.

An autonomous AI research agent based on the MCP protocol, capable of completing the full research process such as web search, knowledge base retrieval, code writing, chart generation, and report writing through a single prompt.

The Stata MCP extension provides Stata integration for VS Code and Cursor, supporting command execution, AI assistance, and real-time output viewing.

This project implements a MATLAB Model Context Protocol (MCP) server, supporting interaction with a shared MATLAB session through a Python interface. It provides functions such as code execution and variable retrieval, and plans to expand support for more tools and data types.

The Dumpling AI MCP Server is a model context protocol server integrating multiple AI functions, providing capabilities such as data scraping, content processing, knowledge management, AI agents, and code execution.

The AutoLISP MCP server for AutoCAD LT controls the generation and execution of AutoLISP code through natural language to achieve automated drawing of engineering drawings.

An MCP server that provides a Python code execution environment, supporting code running, package installation, and file operations, suitable for integration with LLM applications.

The MCP Development Server is a project management tool designed for Claude, providing project context awareness and a Docker code execution environment.

EvolveMCP is an open - source project that enables Claude AI to independently build, install, and use tools, expanding the practical capabilities of AI through Python code execution.

A local SageMath mathematical computing server based on the MCP protocol, providing version query and code execution functions, and supporting dual transport modes of STDIO and HTTP

Sugar is an autonomous execution layer designed for AI programming agents, providing task queue management, 24/7 continuous operation, and a persistent memory system, supporting integration with mainstream AI coding tools such as Claude Code and OpenCode.

AutoMobile is a mobile automation toolset that provides automation testing, UI interaction, test writing, and execution functions for the Android platform. It enables intelligent interaction loops and source code mapping through the MCP server.

A C# code execution MCP server based on Roslyn

A server implementation for interacting with Unreal Engine instances through remote Python execution, supporting node management, remote code execution, and real-time monitoring.

The Modal MCP Toolbox is a collection of tools running on the Modal platform. Based on the Model Context Protocol (MCP), it can provide extended functions for LLMs, such as Python sandbox code execution and FLUX model image generation.