MCP server · Developer tools
ProjectPulse MCP server
by alexbypa
Ask your AI to grade any GitHub project's health, security and build status in plain words.
ProjectPulse is a helper that lets your AI look at a GitHub project and tell you how healthy it is. It gives a simple letter grade from A to F, plus details on security alerts, build results and delivery speed. It is handy if you pick libraries for work, review someone else's code, or just want to know if a project is well kept.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you using what it already learned. An MCP server is a small helper program that gives your AI a new skill or a connection to another service. This one connects your AI to GitHub, so it can look up real, current information about a repository when you ask. You stay in the chat, and the helper does the fetching behind the scenes.
What this MCP server does
You ask your AI something like how healthy a GitHub project is. The AI passes your question to ProjectPulse, which then talks to GitHub and to the OpenSSF Scorecard service. ProjectPulse gathers the numbers, grades them, and hands a clear answer back to your AI. Your AI then explains it to you in normal language, right in the chat.
Click to zoomWhat you can do with it
- Get an A to F health grade for any GitHub repository
- Check Dependabot and code scanning security alerts
- See whether recent CI builds passed or failed
- Compare the health of two to five repositories side by side
- Look at DORA delivery metrics like deployment frequency and lead time
- Check a repo against a 12-point open source best practices list
- View basic repo facts like stars, forks, language and license
Try asking your AI
- “What's the health score of facebook/react?”
- “Compare the health of expressjs/express, fastify/fastify and koajs/koa”
- “Are there any critical dependency vulnerabilities in my-org/my-app?”
- “Show me the DORA metrics for vercel/next.js over the last 60 days”
What it gives back to you
You get back a written answer in your chat, with a score from 0 to 100 and a letter grade, plus a short breakdown of what helped or hurt the score. For security and build questions you get lists of alerts or recent workflow runs with dates and severity. When you ask again about the same repo, it can also show whether the score went up or down since last time.
Before you start
What you need
- Node.js version 18 or newer
- A GitHub personal access token (a kind of password for apps; GitHub gives you one for free). Optional for public repos, but needed for private repos and for security data.
- An MCP-compatible app such as Claude Desktop, Claude Code, Cursor or Windsurf
Good to know
It only reads from GitHub and does not change anything, but it saves small trend snapshots on your own computer, and it needs a GitHub token, so keep that token private and give it read-only access.
Install it with your AI
Add ProjectPulse MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check ProjectPulse MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Developers, tech leads and anyone who has to judge whether a GitHub project is safe and well maintained before using it.
