Awesome AI AgentsMCP Server Framework

bgauryy/octocode-mcp

⭐ 933 TypeScript repository created 2025-06-05

Octocode is a code research platform aimed at AI agents and developers who need to find, understand and prove context across code they own and code hosted on GitHub. It ships one toolset that works over local working copies and remote sources alike: GitHub repositories, pull requests and npm packages. Retrieval combines ripgrep-style text search, AST-aware structural search, directory trees, precise partial file reads and LSP-backed symbol navigation, all driven by a Rust engine so that results stay fast and token-efficient on single files as well as very large monorepos. The project offers two interchangeable interfaces backed by the same tools. As an MCP (Model Context Protocol) server it registers with clients such as Claude Code, Cursor, VS Code, Windsurf, Kiro, Goose and LM Studio, usually through a single npx command or a one-click install link. As a command line tool it is self-describing: running the bare command prints usage and the full tool catalog, so a coding agent can discover and drive it without any MCP wiring. Every MCP tool is also available as a plain subcommand that takes JSON arguments and returns compact YAML, and local paths are routed to local tools while owner/repo arguments are routed to the GitHub tools. Authentication with GitHub is optional but unlocks private repositories and higher API rate limits, with several token sources supported. The documentation also covers configuration, security considerations, language coverage, packaged skills, architecture notes and agent workflow recipes, plus published benchmarks positioning the tool for research-style exploration rather than simple grep. Requirements are Node.js 20.12 or newer. The project is written mainly in TypeScript with a Rust core and is listed as an official community MCP server.

https://github.com/bgauryy/octocode-mcp

mcpcode-searchgithubcliastripgreplsptypescriptrustcode-intelligence

Also in MCP Server Framework

thedaviddias/Front-End-Checklist

Front-End Checklist is an open-source quality system for modern web development, offering comprehensive best practices for humans and AI agents.

PrefectHQ/fastmcp

FastMCP offers a Pythonic framework for building Model Context Protocol (MCP) servers and clients, facilitating structured communication for AI agents and models.

pascalorg/editor

Local-first 3D building editor built with React Three Fiber and WebGPU that exposes an MCP service so AI agents can create and edit 3D scenes.

trycua/cua

c/ua is a high-performance framework that enables AI agents to control full macOS and Linux operating systems within secure, lightweight virtual containers on Apple Silicon Macs, supporting complex autonomous workflows and LLM integration.

nukeop/nuclear

Nuclear is a free, open-source, ad-free music player for Windows, macOS, and Linux, featuring streaming from various sources, playlist management, a powerful plugin system, and integration with AI ...

googleapis/mcp-toolbox

MCP Toolbox for Databases is an open-source server that connects AI agents and applications to enterprise databases using the Model Context Protocol (MCP).

apify/apify-mcp-server

Model Context Protocol server that exposes thousands of Apify Actors as tools, letting AI agents scrape social media, search engines, maps and e-commerce sites over hosted HTTP or local stdio.

grab/cursor-talk-to-figma-mcp

Cursor Talk to Figma MCP is an integration that enables Cursor AI to communicate with Figma programmatically for reading and modifying designs, automating and enhancing the design workflow.