Serena is a powerful open - source coding agent toolkit that can transform LLMs into full - fledged agents that can work directly on codebases. It provides IDE - like semantic code retrieval and editing tools, supports multiple programming languages, and can be integrated with multiple LLMs via the MCP protocol or the Agno framework.

This project is an MCP server for deploying code to Google Cloud Run, supporting deployment through AI agents, IDEs, and assistant applications.

The CodeSandbox MCP server exposes CodeSandbox SDK operations through tools for AI agents to perform operations such as sandbox creation and file read and write.

The Copilot Studio Agent Direct Line MCP Server is a local MCP server that allows developers to directly interact with Microsoft Copilot Studio Agents in their code editors through the Direct Line 3.0 API, providing functions such as conversation management, message sending, and history retrieval.

Codebase MCP is a service that implements the Model Context Protocol (MCP), providing tools for retrieving and analyzing entire codebases through RepoMix, and supporting AI agents such as Cursor's Composer Agent to automatically read and understand large codebases.

AgentREPL.jl is a tool that provides a persistent Julia REPL session for AI agents through the MCP protocol, solving the problems of Julia startup and compilation delays and enabling AI agents to execute code efficiently.

Pushover MCP is a tool that implements the Model Context Protocol specification, allowing AI agents to send notifications via Pushover.net. It provides a simple configuration method and multiple integration methods, and supports use on platforms such as Cursor and Roo Code.

A-MEM is a self-evolving memory system designed for coding agents. It uses a Zettelkasten-style knowledge graph structure, can automatically extract, associate, and evolve memories, supports semantic search and graph traversal, and integrates with agents such as Claude Code through the MCP protocol.

A service implementing the Model Context Protocol (MCP), providing tools for retrieving and analyzing the entire codebase, and supporting AI agents such as Cursor's Composer Agent to automatically read and understand the entire codebase.

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.

OpenManus is an open-source project that allows users to realize various ideas without an invitation code. It was built by members of the MetaGPT team in 3 hours. It provides a simple implementation that allows users to create their own intelligent agents and supports multiple languages and configurations. The project welcomes suggestions, contributions, and feedback. Future plans include better planning, real-time demonstrations, playback functions, RL fine-tuning models, and comprehensive benchmarking.

A plug - and - play Redshift database MCP service that provides a secure and standardized data access interface for LLMs and AI agents, supports multiple permission modes, and can be deployed and used without code modification.

Codeix is a fast semantic code search tool designed for AI code assistants. By building a code index that can be committed to Git, it enables the search for symbols, references, and callers across codebases, improving the code location efficiency of AI agents.

Senior Consult MCP is an MCP server that allows AI agents to consult multiple top - tier models (such as Claude, GPT, Gemini, etc.) to obtain technical architecture suggestions, code reviews, and solutions to complex problems without switching contexts.

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 AI Code Toolkit provides MCP servers and tools to help AI programming agents maintain code consistency, follow conventions, and scale as the codebase expands, including scaffolding templates, architectural patterns, and validation rules

The MCP Backup Server is an instant backup and recovery system designed specifically for AI agents and code editing tools, providing fast security points and context preservation functions.

The Netlify MCP Server is a service that follows the Model Context Protocol (MCP). It allows code agents to use the Netlify API and CLI through natural language instructions to create, build, deploy, and manage Netlify resources.

The Athena Protocol is an intelligent MCP server acting as a technical leader for AI programming agents, providing expert verification, impact analysis, and strategic guidance. It helps AI agents detect problems, validate assumptions, and optimize solutions before code changes, thereby improving code quality, reducing regressions, and making more informed architectural decisions.

A backup and recovery server designed specifically for AI agents and code editing tools, providing fast and secure backup functions, suitable for instant backups before high - risk operations.

The You.com DX Toolkit is an open-source AI development toolkit that includes npm packages, plugins, and skills, and can work in conjunction with more than 20 AI programming assistants such as Claude Code and Cursor. It provides tools such as the MCP server, Vercel AI SDK plugin, and Teams.ai integration, supporting real-time web search, AI agents, and content extraction functions.

This is an MCP server project that allows users to define AI sub - agents for specific tasks (such as code review, test writing) in Markdown files and execute them in any MCP - compatible tool through the Cursor, Claude Code, or Gemini CLI backends, realizing the reuse of AI sub - agent workflows across IDEs.

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.

A service toolset based on the Model Context Protocol, providing functions such as encoding conversion, network diagnosis, system monitoring, security encryption, and QR code generation, and supporting LLM agents to call system tools.

Beads Village is a multi-agent MCP server for task coordination and file locking between AI agents. It combines Beads issue tracking and a built-in mail system, enabling multiple agents to collaborate in the same codebase without conflicts.

The MCP Toolkit is a modular server implementation for building high-precision vertical AI agents, providing support for 123 tools, significantly reducing the amount of code, and simplifying complex workflows.

The official e18e MCP server provides modern, high - performance best - practice suggestions for AI agents, including checking package installation commands, analyzing source code imports, and providing migration guides.

TeaRAGs is a semantic code search MCP server designed for coding agents. It supports large - scale codebases through AST - aware chunking and incremental indexing, and uses Git trajectories (such as 19 signals including code changes, author information, and defect repair rates) for intelligent re - ranking, surpassing traditional embedding similarity retrieval.

The Authenticator App MCP Server is a secure MCP (Model Context Protocol) server that enables AI agents to interact with the Authenticator App, seamlessly obtain 2FA codes and passwords, help automate the login process, and maintain security.

Agents Council is an AI agent collaboration tool based on the MCP protocol, which allows different AI agent sessions (such as Claude Code, Codex, Gemini, etc.) to communicate and collaborate across sessions without additional infrastructure. It realizes communication between agents through a central MCP server, supports session retention, human - participation monitoring, summoning of Claude agents, etc., to help developers solve complex tasks.

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.

Flutter - skill is an AI - native end - to - end testing tool that allows AI agents to directly interact with running applications through the MCP protocol, supporting 10 platforms without writing test code.

Agent Farm v3.4 is a system based on AI agent evolution and parallel task execution, which realizes task processing through tool - enhanced agents. The new version introduces the chunked write mode, supports the parallel generation of large documents and code files, improves performance by 8.6 times, and uses local models for result synthesis without relying on cloud tokens.

An MCP server for TypeScript type checking and code navigation, providing real - time type checking and code navigation functions for AI programming agents through the LSP of tsgo

The Maven Indexer MCP Server provides a tool for AI agents to search for Java classes, method signatures, and source code by indexing the local Maven repository and Gradle cache, especially suitable for understanding the code of internal private libraries and less - known public libraries.

Unity Code MCP is a high - performance MCP server built on Rust, designed for AI agents to independently write Unity code, providing lightweight and efficient compilation feedback and test execution capabilities.

MCP (Model Context Protocol) is a standardized protocol that enables AI agents to seamlessly communicate with various tools and services. GitHub integration provides repository management, code operations, issue management, and collaboration features.

This is a prototype of a code execution server based on the MCP protocol, which combines the code generation capabilities of large language models with MCP tool integration, enabling AI agents to run Python code in an isolated sandbox and invoke external tools.

This project provides a middleware/control plane (MCP) server that allows code agents to securely execute queries on multiple databases while protecting database credentials. It manages connection configurations through an SQLite database, supports databases such as PostgreSQL, MySQL, MongoDB, and Oracle, and provides integration tools with AI agents such as Gemini and Claude.

A high - performance batch code understanding MCP toolkit optimized for Java, providing panoramic context, structural mapping, and precise positioning functions to help AI agents efficiently explore large codebases.