MCP Open-Source Projects

Showing 40 indexable projects from the current snapshot.

• koala73/worldmonitor

  A situational awareness application that consolidates over 65 external data providers and 500 news feeds into AI-synthesized briefs and multi-layered geospatial maps. It provides a native desktop interface, API access via an MCP server, an…

• diegosouzapw/OmniRoute

  A self-hosted AI gateway that aggregates 250+ providers into a single endpoint with auto-fallback routing and token compression. It is suited for developers and AI engineers who need to consolidate multiple API keys, manage rate limits, an…

• HKUDS/Vibe-Trading

  An open-source research workspace that translates natural-language prompts into market-data loading, strategy drafting, backtesting, and report generation. It targets developers and data teams building research and analysis workflows acros…

• alibaba/page-agent

  An in-page JavaScript GUI agent that enables natural language control of web interfaces via a single script, operating directly on the DOM without requiring browser extensions, Python, or headless browsers.

• every-app/open-seo

  A self-hostable, pay-as-you-go SEO application that provides keyword research, rank tracking, competitor insights, backlink analysis, site audits, and AI visibility. It exposes an MCP server for AI agents and requires a paid third-party Da…

• affaan-m/ECC

  A system of over 260 reusable skills, rules, and hooks designed to standardize AI-assisted software development across multiple agent harnesses. It provides cross-harness automations, a security scanner for agent configurations, and an exp…

• n8n-io/n8n

  n8n is a source-available platform for building and deploying AI agents and workflow automation using a visual canvas combined with custom code. It offers 1500+ integrations and can be self-hosted or deployed via a managed service.

• f/prompts.chat

  An open-source prompt library providing browsable, downloadable prompt examples for AI chat models, along with a CLI-driven path to deploy a private, branded instance. It targets general users, developers, and educators who need to find, s…

• langflow-ai/langflow

  Langflow is a visual authoring environment for designing, testing, and deploying AI agents and workflows. It supports turning visual flows into APIs, JSON exports, and MCP servers, with component-level customization available through Pytho…

• Shubhamsaboo/awesome-llm-apps

  A repository of over 100 open-source AI agent and RAG application templates, organized across multiple domains such as voice, generative UI, and coding tools. It serves as a reference for developers and general users seeking tested startin…

• BerriAI/litellm

  LiteLLM provides a unified gateway and Python SDK for calling 100+ LLM providers using the OpenAI format, addressing the operational complexity of managing disparate SDKs and authentication patterns. It includes production-ready features s…

• modelcontextprotocol/servers

  A collection of official reference implementations for the Model Context Protocol, managed by the MCP steering group. Developers can use these servers to learn MCP features, evaluate official SDKs, and build their own custom servers.

• google-gemini/gemini-cli

  google-gemini/gemini-cli is a terminal-first AI agent that brings Gemini models into the command line for code understanding, generation, and workflow automation. It provides file operations, shell commands, web fetching, and extensibility…

• Graphify-Labs/graphify

  Graphify converts local project directories into queryable knowledge graphs using deterministic tree-sitter AST parsing across approximately 40 programming languages without requiring LLM calls. It outputs an interactive HTML visualization…

• crewAIInc/crewAI

  CrewAI is a Python framework for orchestrating role-playing, autonomous AI agents in production workflows. It provides high-level abstractions and low-level APIs to combine autonomous agent teams with event-driven control flows.

• punkpeye/awesome-mcp-servers

  awesome-mcp-servers is a curated, categorized directory of Model Context Protocol (MCP) servers, including both production-ready and experimental options, alongside related clients, tutorials, and frameworks. It helps users discover and na…

• CherryHQ/cherry-studio

  A desktop client that consolidates access to multiple cloud and local LLM providers alongside pre-configured AI assistants and document processing. It targets general users, developers, and enterprise teams who need a unified local-chatgpt…

• thedotmack/claude-mem

  claude-mem preserves context for Claude Code across sessions by automatically capturing tool usage, generating semantic summaries, and injecting relevant context into future sessions. It addresses the loss of knowledge continuity when AI a…

• microsoft/autogen

  AutoGen is a multi-agent AI orchestration framework currently in maintenance mode. It provides layered APIs for prototyping autonomous agent workflows, but new production projects should use Microsoft Agent Framework instead.

• lobehub/lobehub

  LobeHub is a self-hostable, web-based application that treats AI agents as collaborative teammates with structured, editable memory. It requires an OpenAI API key and involves paid external service costs.

• Unstructured-IO/unstructured

  This project provides open-source components for ingesting and pre-processing unstructured data into structured outputs for large language models. It offers modular document partitioning across multiple file types and includes a Model Cont…

• D4Vinci/Scrapling

  An adaptive web scraping framework for Python that relocates elements after website changes, bypasses anti-bot systems, and automates dynamic content extraction. It supports self-hosted local runs via Python or Docker and requires Python 3…

• OpenBB-finance/OpenBB

  OpenBB provides a connect-once infrastructure layer that consolidates proprietary, licensed, and public financial data for consumption across Python environments, OpenBB Workspace, Excel, REST APIs, and MCP servers for AI agents.

• microsoft/ai-agents-for-beginners

  An 18-lesson course that teaches the fundamentals of building AI agents through written guides, videos, and Python code samples. It covers core topics from design patterns to production deployment using Microsoft Agent Framework.

• xtekky/gpt4free

  This project aggregates multiple LLM and media generation providers behind a unified OpenAI-compatible interface. It provides Python and JavaScript clients, a local GUI, a REST API, and an MCP server under a community-first license.

• ruvnet/ruflo

  Ruvnet/ruflo adds an execution and coordination layer around Claude Code and OpenAI Codex, providing specialized agents, coordinated swarms, self-learning memory, and zero-trust federation. It targets developers and enterprise teams who ne…

• docling-project/docling

  docling-project/docling parses diverse document formats—including PDF, DOCX, PPTX, XLSX, HTML, images, and audio—and prepares them for generative AI applications. It provides advanced PDF understanding, a unified document representation fo…

• Panniantong/Agent-Reach

  Agent Reach gives AI agents a capability layer for reading and searching content across internet platforms without paid API keys. It selects and maintains stable access methods for platforms affected by API paywalls, IP blocks, and anti-sc…

• sansan0/TrendRadar

  A lightweight public opinion and trending topic monitor that aggregates multi-platform data and RSS feeds with keyword and AI-based filtering, routing alerts to channels such as Telegram. It relies on external APIs for data and an LLM via…

• upstash/context7

  Context7 injects current, version-specific library documentation and code examples into LLM prompts, addressing hallucinated or outdated API usage. It operates as an MCP server or CLI tool integrated into coding agents, relying on a privat…

• MemPalace/mempalace

  mempalace/mempalace is a local-first AI memory application that stores conversation history verbatim, preventing context loss during AI coding sessions. It provides scoped semantic search, pluggable storage backends, and 36 MCP server tool…

• zylon-ai/private-gpt

  zylon-ai/private-gpt provides an API-first backend layer that follows the Claude API model to build applications on local models without rebuilding backend primitives or relying on cloud APIs. It requires a separately hosted OpenAI-compati…

• mvanhorn/last30days-skill

  An AI agent skill that searches across disconnected social and media platforms in parallel, scores results by human engagement signals, and synthesizes a grounded brief. It requires external internet access to operate.

• aaif-goose/goose

  Goose is a general-purpose AI agent that runs natively on your machine via a desktop app, CLI, or API. It supports multiple LLM providers and MCP extensions for diverse tasks beyond code suggestions.

• mudler/LocalAI

  LocalAI is a self-hosted AI engine that runs large language, vision, audio, image, and video models behind a single API without requiring a GPU. It provides drop-in OpenAI, Anthropic, and ElevenLabs API compatibility while keeping data wit…

• ChromeDevTools/chrome-devtools-mcp

  chrome-devtools-mcp connects an MCP client to a live Chrome browser for automation, debugging, and performance analysis. It runs locally through Node.js and is designed around Google Chrome or Chrome for Testing.

• jamiepine/voicebox

  VoiceBox is a local-first, open-source voice I/O application that combines voice cloning, multi-engine text-to-speech, global dictation, and AI agent output. It runs entirely on your machine, ensuring voice data and captures are never tran…

• HKUDS/nanobot

  A self-hosted personal AI agent runtime for integrating chat channels, tools, memory, and automations. It provides a small, extensible core that runs locally or on a server and requires an OpenAI-compatible LLM provider.

• zhayujie/CowAgent

  CowAgent is a 24/7 AI assistant and agent harness that supports task planning, long-term memory, multi-channel messaging, and multi-model routing. It is suitable for developers and general users who need a persistent, extensible agent conn…

• rohitg00/ai-engineering-from-scratch

  A 503-lesson open-source curriculum spanning 20 phases that builds AI engineering knowledge from mathematical foundations to production agents. Learners produce a reusable artifact for every lesson and can install generated skills into age…