Open Source MCP Projects
Discover 182 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 Developer Tools. Last updated October 4, 2026.
182 repositories · updated October 4, 2026
opik-mcp: Connect AI Assistants to Opik
opik-mcp is a Python MCP server that lets AI coding assistants work with an Opik workspace. Use it to inspect traces, record scores, manage prompts, and explore evaluation data through natural-language workflows.
QueryWeaver: Turn Natural-Language Questions into SQL
QueryWeaver converts plain-English questions into SQL by using a graph representation of database schemas. It suits teams that want a self-hosted Text2SQL web app, REST API, MCP interface, or Python SDK for PostgreSQL and MySQL.
jan: Run AI Models Locally or Connect to Cloud Models
Jan is a desktop AI assistant for downloading and running language models on your computer, with optional connections to cloud providers. It suits people who want local control and privacy alongside custom assistants and an OpenAI-compatible local API.
LocalAI: Run AI Models on Your Own Hardware
LocalAI serves language, vision, audio, and image models through compatible APIs on local or distributed hardware. It suits developers and teams who want a flexible self-hosted AI service without depending on a GPU.
Hexabot: Build and Run AI Workflows Across Chat Channels
Hexabot is a TypeScript platform for building agentic workflows that combine actions, tools, memory, and conversational channels. It suits teams that want to develop and operate AI automations in a single runtime.
inspector: Test and Debug MCP Servers and Apps
MCPJam Inspector helps developers test, inspect, and evaluate MCP servers and apps across clients and models. Use it to debug protocol and OAuth behavior, run repeatable evaluations, and check for regressions in CI.
mcpo: Turn MCP Tools into OpenAPI Services
mcpo proxies MCP servers as standard HTTP APIs with generated OpenAPI schemas and interactive docs. It is useful when agents, apps, or teams need to use MCP tools through familiar REST interfaces.
deepagents: Build Agents with Planning and Tooling Built In
Deep Agents is a Python agent harness for building LLM agents with planning, delegation, file access, and context management built in. It suits developers who need a more capable starting point than a minimal agent loop, while retaining control over models and tools.
mcp-ui: Build Interactive Interfaces for MCP Tools
mcp-ui provides SDKs for attaching web interfaces to Model Context Protocol tools and rendering them in compatible hosts. Use it when an MCP server needs interactive, sandboxed UI alongside tool results.
modelcontextprotocol: Define a Standard for AI Tool Connections
Model Context Protocol (MCP) defines a shared protocol for connecting AI applications with tools and context providers. This repository contains the specification, protocol schema, and official documentation for implementers and users.
chat-ui: Build a Web Interface for OpenAI-Compatible LLMs
Chat UI is a SvelteKit application for chatting with models through OpenAI-compatible APIs. It powers HuggingChat and can be self-hosted with a compatible model service, optional MongoDB, and configurable tools.
mcp-server-cloudflare: Connect AI Clients to Cloudflare Services
A collection of domain-specific Model Context Protocol servers that let compatible AI clients inspect and work with Cloudflare services through guided tools. Use them when you want product-focused interactions rather than broad API access through code execution.