Open Source MCP Projects
Discover 104 open source MCP repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. MCP projects here are most often combined with AI Agents, TypeScript and AI. Last updated October 3, 2026.
104 repositories · updated October 3, 2026
ADR: Secure and Monitor Enterprise AI Agents
ADR is an enterprise security toolkit for discovering AI tools, collecting agent activity, benchmarking defenses, and detecting risky behavior. It is aimed at security teams evaluating or monitoring AI agents across employee endpoints and customer-facing systems.
OpenSandbox: Run AI Agents in Isolated Sandboxes
OpenSandbox provides isolated environments where AI applications can run code, commands, and browser or desktop tasks. It supports local Docker use and Kubernetes deployment through a shared sandbox API.
cortex-mem: Give AI Agents Persistent Long-Term Memory
Cortex Memory is a Rust framework for storing, extracting, and searching long-term memories for AI agents and applications. It combines durable file-based storage with semantic search, and offers CLI, REST API, and MCP access.
ruflo: Coordinate AI Agents and Autonomous Workflows
Ruflo is a TypeScript agent harness for Claude Code and Codex. It adds coordinated agent teams, persistent memory, workflow automation, and MCP integrations for developers building multi-agent systems.
fastmcp: Build MCP Servers, Clients, and Apps in Python
FastMCP is a Python framework for building Model Context Protocol servers, clients, and interactive apps. It turns Python functions into MCP tools and manages protocol details such as schemas, transport, and authentication.
clowder-ai: Coordinate AI Agents as a Collaborative Team
Clowder AI adds a platform layer for coordinating agent CLIs from multiple model families. It is for developers who want agents to retain roles and shared memory, communicate with one another, and review each other’s work.
goose: Run an Extensible AI Agent on Your Machine
goose is a Rust-based AI agent available as a desktop app, CLI, and API. It connects to multiple LLM providers and MCP extensions, making it useful for code work as well as research, writing, automation, and data analysis.
lobehub: Organize and Run Teams of AI Agents
LobeHub is a web app for building, coordinating, and scheduling AI agents as a team. It suits individuals and teams who want shared agent workflows, model choice, and self-hosting, but requires configuring an AI model provider.
QwenPaw: Run a Self-Hosted Personal AI Assistant
QwenPaw is a personal AI assistant that runs locally or in the cloud and connects to chat apps, models, and extensible tools. It suits people who want a customizable agent with persistent memory and security controls under their own deployment.
ReMe: Manage Persistent Memory for AI Agents
ReMe turns agent conversations and resources into searchable, editable Markdown memory that can evolve over time. It suits developers building assistants that need reusable knowledge across sessions and agent runtimes.
ext-apps: Standard for UIs Embedded in AI Chatbots with MCP Protocol
MCP Apps provides a standardized way to deliver interactive UIs from MCP servers, rendering inline in compliant chat clients like Claude and ChatGPT. This repository contains the official specification and SDK for building these interactive UIs. It enables developers to create rich user experiences, such as charts, forms, and dashboards, directly within AI chatbot conversations.
zero: Run a Local Terminal Coding Agent
Zero is a Go-based terminal coding agent that can inspect and edit repositories, run commands, and work with many hosted or local models. It suits developers who want scriptable coding assistance with local sessions and explicit controls over side effects.