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 tool that exposes a secure local Python executor through the MCP protocol, providing code interpreter functionality for LLM applications

An MCP server that provides remote pexpect session control, supporting programmatic interactive debugging with command-line debugging tools such as LLDB and GDB through Python code

CICADA is an MCP server that provides structured code indexing for AI code assistants. Through AST-level indexing, call site tracking, and semantic search, it provides efficient context compression for Elixir, Python, and Erlang code repositories, reducing token usage and improving the quality of code understanding.

An MCP server for analyzing the structure, complexity, and dependencies of Python code.

A RAG system based on Python code analysis. It parses the code structure through AST and stores it in the Weaviate vector database, providing code query, natural language Q&A, and visualization functions, and supporting multi-codebase management and dependency analysis.

The project involves documentation, sample code repositories, and community resources for the LangChain framework, including technical content such as Python programming, AI agent development, FastAPI integration, and LLM fine-tuning.

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.

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.

This project demonstrates how to debug the MCP server in VSCode, includes example code for Python and TypeScript, and integrates the MCP Inspector tool for browser testing.

A Python tool for converting CHM help files to Markdown format, supporting code highlighting, table preservation, and batch processing, facilitating version management of technical documents.

Fused MCP Agents is a Python - based tool that allows users to directly run any Python code through the Claude desktop application, enabling the connection between LLMs, APIs, and executable code.

A text editor server built on Python and FastMCP, providing powerful file operation tools. It enables file reading, editing, and management through a standardized API, and specifically optimizes the accuracy and reliability of code editing by AI assistants.

JEBMCP is a project that combines JEB and MCP tools, aiming to simplify reverse engineering tasks through Python scripts and provide efficient code analysis and operation functions.

This is a VS Code-based MCP server template project for external reconnaissance tasks. The project uses the uv tool for environment management and dependency installation, supports Python 3.11+ versions, and includes the dnspython dependency and a custom external-recon.py script.

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.

An experimental local code indexing service based on Python that uses ChromaDB for storage and provides semantic search functionality, serving tools such as Cursor through the MCP protocol.

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.

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.

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

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

A skill management system based on the MCP protocol, allowing AI assistants such as Claude to create, edit, run, and manage skill scripts stored in the local directory, supporting Python code execution, environment variable management, and multi - skill combined use.

ipybox is a lightweight Python code execution sandbox based on IPython and Docker, supporting secure code execution in local or remote environments. It is suitable for data analysis and code execution scenarios of AI agents.

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

The MCP Code Executor is a server that allows LLMs to execute Python code in a specified Conda environment.

An MCP server that provides stateful Django shell interaction for AI assistants, allowing direct execution of Python code in a Django project and maintaining session state

A Python MCP server for extracting and analyzing Python code structure, focusing on the import/export relationships between files, providing a lightweight implementation without the need for a proxy system.

An MCP server based on the NVIDIA USDCode API, providing an AI assistant tool for Isaac Sim script writing, USD operations, Python code snippets, and API usage assistance.

Gossiphs is a zero-configuration, high-performance general code file relationship analysis tool that supports multiple programming languages. It is based on tree-sitter and git analysis, provides support for Python SDK and MCP protocol, and is convenient for integration with AI.

An MCP server based on the Deno sandbox, allowing for the secure execution of TypeScript, JavaScript, and Python code locally, providing a secure execution environment with permission control.

JADX-MCP-SERVER is a Python server that works with the JADX-AI-MCP plugin, enabling LLM (such as Claude) to analyze decompiled Android APK code in real-time through the MCP protocol, providing reverse engineering functions such as vulnerability detection and code understanding.

The MCP Python Interpreter is a service that allows LLMs to interact with a Python environment, providing functions such as code execution, file operations, and package management, and supporting multiple development workflows.

RagCode MCP is a privacy-first local AI code assistant that enables AI assistants to understand the entire codebase through semantic vector search and RAG technology. It supports multiple languages such as Go, PHP, and Python, without relying on the cloud.

The Python MCP Sandbox is an interactive Python code execution tool that allows users to securely execute Python code and install packages in isolated Docker containers.

An MCP protocol server implementation based on Pyodide, providing Python code execution capabilities for large language models

An MCP server for executing Python code and managing Python packages, providing a secure execution environment, package management, resource monitoring and other functions

Python MCP Sandbox is an interactive code execution tool that can securely run Python code and manage packages in isolated Docker containers

A simple MCP server built with Python, providing two example tools: converting company names to stock codes and obtaining financial data from Yahoo Finance, mainly used for learning the construction and operation of MCP servers.

code-to-tree is an MCP server that can accurately convert source code in multiple programming languages into Abstract Syntax Trees (ASTs). It supports C, C++, Rust, Ruby, Go, Java, and Python languages, uses the tree-sitter parser, and provides a standalone executable file.

An MCP protocol service implemented in Python that provides a standardized API to execute Python code