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
joinly: Let AI Agents Join and Participate in Meetings
Joinly connects AI agents to live video meetings through an MCP server, enabling them to listen, speak, chat, and use tools. It suits developers building meeting-aware agents who want a self-hosted setup and can manage its provider credentials and local runtime.
fast-agent: Build and Run LLM Agents and Workflows
fast-agent is a Python framework and CLI for building, running, and evaluating LLM agents. It connects agents to MCP servers and supports multi-agent workflows, multiple model providers, and interactive terminal use.
mcp-server-chart: Generate Charts Through MCP
A TypeScript MCP server that lets AI clients generate AntV visualizations and use them for data analysis. It suits people who want chart generation as an MCP tool, with support for more than 25 chart types and multiple transports.
bolt.diy: Build Full-Stack Apps with Your Choice of LLM
bolt.diy is a browser-based AI coding workspace for creating, editing, and deploying Node.js web applications. It connects to many hosted and local model providers, making it useful when you want control over which LLM powers your development workflow.
vexa: Capture and Transcribe Online Meetings
Vexa runs bots that join Google Meet, Microsoft Teams, and Zoom, then provides speaker-attributed transcripts through an API. Teams can use its hosted service or self-host the stack and connect transcripts to workspace agents.
linctl: Manage Linear Issues from the Command Line
linctl is a Go CLI for managing Linear issues, projects, teams, users, and comments. It suits developers and agents that need scriptable access to Linear through JSON output, GraphQL, or schema-driven MCP commands.
Memori: Give AI Agents Persistent Memory
Memori adds structured, persistent memory to LLM applications by capturing agent execution and conversations. Its Python and TypeScript SDKs integrate with existing models and data infrastructure, with managed cloud and BYODB options.
local-deep-research: Research with Local or Cloud AI
Local Deep Research turns complex questions into cited reports by coordinating LLMs with web, academic, and private-document search. It suits researchers and privacy-conscious teams who want a self-hostable tool and control over models and data.
wassette: Run WebAssembly Tools Through MCP
Wassette lets AI agents load and use WebAssembly Components through the Model Context Protocol. It is aimed at developers who want reusable tools running in Wasmtime’s security sandbox, but the project warns that it is not production-ready.
deepscrape: Scrape Websites and Extract Structured Data
DeepScrape is a self-hosted TypeScript service for scraping and crawling websites, returning clean content or structured data. It combines HTTP fetching, Playwright, optional LLM extraction, and APIs for building data pipelines and agent workflows.
typescript-sdk: Build Model Context Protocol Clients and Servers
The official TypeScript SDK for building Model Context Protocol clients and servers. It provides transports, server and client libraries, and optional framework adapters for applications that exchange context with LLMs through MCP.
wordpress-mcp: Connect WordPress to MCP
An archived PHP project for adding Model Context Protocol support to WordPress. It is retained for historical reference; new integrations should use the WordPress mcp-adapter project and current setup documentation.