SaaSHub helps you find the best software and product alternatives Learn more β
Top 23 model-context-protocol Open-Source Projects
-
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
mcp-for-beginners
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.
Project mention: Host Your Node.js MCP Server on Azure Functions in 3 Simple Steps | dev.to | 2025-12-09π¨ Free course alert! If you're new to MCP, check out the MCP for Beginners course to get up to speed quickly.
-
unity-mcp
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Community projects, like those from CoplayDev and CoderGamester, focus on speed and flexibility. They expose many parts of the Unity editor as MCP tools, which makes them great for experimentation and fast iteration.
-
Project mention: Show HN: MCP-C β cloud platform for running MCP agents and apps | news.ycombinator.com | 2025-10-28
-
-
cursor-talk-to-figma-mcp
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
MCP Cursor Talk To Figma - a bit more demanding to set up (you need to set up a local server following the instructions and run the "Cursor Talk To Figma" plugin in Figma; works even without Dev Mode access).
-
firecrawl-mcp-server
π₯ Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Project mention: Show HN: MCP-recorder β VCR.py for MCP servers. Record, replay, verify | news.ycombinator.com | 2026-03-06--target https://mcp.devhelm.io
It works with both HTTP and stdio transports. Scenarios are defined in YAML so it works with MCP servers in any language, and there's a pytest plugin if you want tighter integration. Secret redaction and environment variable interpolation are built in.
To make sure this actually works on real codebases, I submitted several PRs to production MCP servers: monday.com's MCP server (https://github.com/mondaycom/mcp/pull/222), Tavily's MCP server (https://github.com/tavily-ai/tavily-mcp/pull/113), and Firecrawl's MCP server (https://github.com/firecrawl/firecrawl-mcp-server/pull/175). They went from zero schema coverage to full tool surface verification with a clean schema diff available on each tool change. One big benefit is that you can do verification and replay with no API keys β deterministic responses, no live requests to real servers.
I wrote up a deeper dive into the schema drift problem and the VCR pattern for MCP here: https://devhelm.io/blog/regression-testing-mcp-servers
-
awesome-mcp-servers
Awesome MCP Servers - A curated list of Model Context Protocol servers (by appcypher)
Project mention: Top 17 Claude Code OSS Tools! Complete Guide to GitHub Open Source Dev Environments | dev.to | 2025-12-2914. Awesome MCP Servers β 5k
-
XcodeBuildMCP
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
(Optional, but recommended) Install XcodeBuildMCP for the simulator-driving parts. Pairs nicely.
-
openagent
β‘οΈnext-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org
Project mention: I Built a Single-File AI Agent in Go β Zero Dependencies, Double-Click to Run | dev.to | 2026-05-18GitHub: github.com/the-open-agent/openagent β
-
mcp-context-forge
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
Project mention: Every AI toolchain is inventing its own safety layer. We shipped one that works across all of them. | dev.to | 2026-05-12Anthropic shipped Claude Code hooks β PreToolUse, PostToolUse, Notification, and friends. They run as subprocesses, get JSON on stdin, and decide whether the tool call proceeds. OpenAI ships tool guardrails in the Agents SDK β Python (and now TS) callables you attach to a tool, with tripwire booleans that abort the run. The MCP ecosystem is sprouting gateways and proxies for the same purpose: MCPX, IBM ContextForge, Microsoft's MCP Gateway, Lasso Security's MCP Gateway β all reasonable answers to the same wire-level question.
-
Unity-MCP
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free. (by IvanMurzak)
-
codebase-memory-mcp
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph β average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Project mention: Show HN: Semble β Code search for agents that uses 98% fewer tokens than grep | news.ycombinator.com | 2026-05-17Would this replace something like codebase-memory-mcp[1] or improve when both is being used?
[1] - https://github.com/DeusData/codebase-memory-mcp
-
-
My current list, am I missing any?
https://github.com/metatool-ai/metamcp
-
ghidra-mcp
Ghidra MCP Server β 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.
Project mention: MCP's Dark Secret: 5 Hidden Patterns Nobody Teaches You About Context Window Optimization | dev.to | 2026-04-30# Lazy-loading MCP: Only activate server when actually needed # Inspired by GhidraMCP's lazy tool loading pattern # https://github.com/bethington/ghidra-mcp class LazyMCPLoader: def __init__(self, server_registry: dict): # Server registry stores metadata, NOT active connections self.server_registry = server_registry self.active_servers = {} async def invoke(self, tool_name: str, params: dict): server_name = self._resolve_server(tool_name) # Lazy initialization β server starts only on first use if server_name not in self.active_servers: print(f"π Lazy-loading MCP server: {server_name}") self.active_servers[server_name] = await self._start_server( self.server_registry[server_name] ) return await self.active_servers[server_name].invoke(tool_name, params) async def invoke_batch(self, tools: list): """Pre-warm servers for tools likely to be used together""" servers_needed = {self._resolve_server(t['tool']) for t in tools} for srv in servers_needed: if srv not in self.active_servers: self.active_servers[srv] = await self._start_server( self.server_registry[srv] ) # Now all servers are pre-warmed for parallel execution return await asyncio.gather(*[ self.active_servers[self._resolve_server(t['tool'])].invoke(t['tool'], t['params']) for t in tools ]) # Register servers β this is ALL that loads into context at startup # 500 bytes vs 50,000 bytes of tool definitions SERVER_REGISTRY = { "github": {"host": "localhost", "port": 3100, "tools": 23}, "filesystem": {"host": "localhost", "port": 3101, "tools": 8}, "ghidra": {"host": "localhost", "port": 3102, "tools": 110}, # Lazy loaded }
-
gemini-mcp-tool
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
Project mention: gemini-mcp-tool VS onequery - a user suggested alternative | libhunt.com/r/gemini-mcp-tool | 2026-06-01 -
toolhive
ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.
I've bumped into the Stacklok/ToolHive folks at a couple of conferences and finally had time to try out their project today. Initial thoughts are pretty positive.
-
mcphub.nvim
An MCP client for Neovim that seamlessly integrates MCP servers into your editing workflow with an intuitive interface for managing, testing, and using MCP servers with your favorite chat plugins.
Project mention: Show HN: Playwright Skill for Claude Code β Less context than playwright-MCP | news.ycombinator.com | 2025-10-20 -
mcp-unity
Model Context Protocol (MCP) plugin to connect with Unity Editor β designed for Cursor, Claude Code, Codex, Windsurf and other IDEs
Community projects, like those from CoplayDev and CoderGamester, focus on speed and flexibility. They expose many parts of the Unity editor as MCP tools, which makes them great for experimentation and fast iteration.
-
pilot-shell
How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make your agents production-ready.
Project mention: Claude Pilot β Claude Code is powerful. Pilot makes it reliable | news.ycombinator.com | 2026-02-23 -
mcp-language-server
mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.
Project mention: Typed languages are better suited for vibecoding | news.ycombinator.com | 2025-08-03Interesting, so an LSP MCP like this?: https://github.com/isaacphi/mcp-language-server
Also interesting note on the docs, though, Claude does try to use cargo doc by itself sometimes.
I was actually wondering why GritQL did not have an MCP, this seems like a natural fit. Would be interested to know if this works for you.
I'm always a bit hesitant to add things to the long term context as it feels very finicky to not have it be ignored and having more seems to make it more likely to be ignored. Instead I usually just repeat myself.
Thank you for the answer, seems there is still lots of things to try.
-
code-mode
π Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
Project mention: Code-Mode Library: First library for tool calls via code execution | news.ycombinator.com | 2025-11-23
model-context-protocol discussion
model-context-protocol related posts
-
Pay for Any API from Inside Claude with Base MCP + APIbase
-
Vibecoding Our First MCP Server
-
From mock-only-works to real-world-works: 48 hours of reCAPTCHA debugging
-
Show HN: Prism Coder β Qwen3.5-14B fine-tuned for MCP tool-routing decisions
-
One MCP server, four clients, zero translation apps open in browser tabs
-
Show HN: Semble β Code search for agents that uses 98% fewer tokens than grep
-
When handoff.md Stops Being Enough for AI Agents
-
A note from our sponsor - SaaSHub
www.saashub.com | 7 Jun 2026
Index
What are some of the best open-source model-context-protocol projects? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | fastmcp | 25,469 |
| 2 | mcp-for-beginners | 16,297 |
| 3 | unity-mcp | 10,377 |
| 4 | mcp-agent | 8,353 |
| 5 | Upsonic | 7,870 |
| 6 | cursor-talk-to-figma-mcp | 6,811 |
| 7 | firecrawl-mcp-server | 6,503 |
| 8 | awesome-mcp-servers | 5,581 |
| 9 | XcodeBuildMCP | 5,452 |
| 10 | openagent | 5,150 |
| 11 | mcp-context-forge | 3,814 |
| 12 | Unity-MCP | 3,016 |
| 13 | codebase-memory-mcp | 2,971 |
| 14 | markdownify-mcp | 2,725 |
| 15 | metamcp | 2,379 |
| 16 | ghidra-mcp | 2,249 |
| 17 | gemini-mcp-tool | 2,227 |
| 18 | toolhive | 1,854 |
| 19 | mcphub.nvim | 1,770 |
| 20 | mcp-unity | 1,749 |
| 21 | pilot-shell | 1,738 |
| 22 | mcp-language-server | 1,539 |
| 23 | code-mode | 1,474 |