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
core: Build and Extend AI Agents
Cheshire Cat AI is a Python framework and microservice for building conversational AI agents. It is aimed at learning, research, and publishing agents, with a local UI and REST API for exploring and extending them.
mcp-bear: Connect AI Clients to Bear Notes
mcp-bear is a Python MCP server that lets compatible AI clients interact with Bear notes through Bear’s X-callback-url actions. It is archived and is largely superseded by Bear’s built-in MCP server.
java-sdk: Build MCP Clients and Servers in Java
The official Java SDK for building Model Context Protocol clients and servers. It provides transport and JSON integration options for Java applications that need to exchange requests, notifications, and streaming data with MCP services.
annas-mcp: Search and Download Documents with MCP or CLI
annas-mcp is a Go MCP server and command-line tool for searching books and articles in Anna's Archive and downloading selected documents. It suits MCP users and terminal workflows, with API access required for downloads.
kong: Route and Govern API, AI, and MCP Traffic
Kong Gateway is a cloud-native proxy for routing and managing API traffic, with features for LLM and MCP gateways. It suits teams that need a configurable gateway for services across Kubernetes or other infrastructure.
android-mcp-server: Control Android Devices Through MCP
A Python MCP server that lets compatible clients inspect and control Android devices through ADB. It suits developers and agent workflows that need device commands, screenshots, UI details, or package information.
MCPJungle: Manage MCP Servers Through One Gateway
MCPJungle is a self-hosted gateway for registering MCP servers and connecting AI clients through a single endpoint. It suits individuals consolidating local setups and teams that need shared discovery, access control, and observability.
webiny-js: Build a Self-Hosted CMS on AWS
Webiny is a TypeScript CMS framework deployed in your own AWS account using serverless services. It suits teams that need customizable content APIs, tenant isolation, and infrastructure control, but requires AWS and development skills.
brightdata-mcp: Give AI Agents Access to Web Data
Bright Data MCP connects MCP-compatible agents to web search, scraping, structured extraction, and remote browser automation. It suits teams that need current public-web data without managing proxies or browser infrastructure, using a Bright Data API token.
mcp: Connect AI Tools to AWS Services
awslabs/mcp is a collection of Python MCP servers that connect AI clients to AWS documentation and services. It suits developers who want AWS-specific context and workflows in MCP-compatible assistants, with permissions and setup varying by server.
Figma-Context-MCP: Give Coding Agents Access to Figma Designs
Figma-Context-MCP is an MCP server that turns Figma file data into concise layout and styling context for AI coding agents. It is intended for developers who want agents such as Cursor to implement designs using design metadata rather than screenshots alone.
obsidian-smart-composer: Add Vault-Aware AI Writing to Obsidian
Smart Composer is an Obsidian plugin for chatting with AI using selected vault notes, searching notes semantically, and applying suggested edits. It suits writers and researchers who want AI assistance inside their note workflow, with hosted or local model options.