MCP server · Health and learning
Phi Longevity MCP server
by Philongevity
Let your AI check sample lab values and suggest guideline-cited next steps for chronic conditions.
This is a helper that connects your AI to the Phi Longevity PRISM engine, which reads lab values and points out what may be missing or overdue, with the guideline quoted. It is handy if you or someone you help is managing a long-term condition like type 2 diabetes, kidney disease, lupus, or life after cancer, and you want plain, sourced talking points for a doctor visit. Note that it only takes made-up or de-identified values, not real health records.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to a service, and here that service is Phi Longevity's PRISM engine. Once connected, your AI can send a set of lab values to this helper when you ask, and the helper comes back with guideline-cited notes you can read in the chat. You do not have to learn anything technical; you just talk to your AI like always.
What this MCP server does
You ask your AI something like whether certain lab numbers look fine for someone managing type 2 diabetes. Your AI sends those numbers to this helper, and the helper passes them to the PRISM engine. The engine compares them against clinical guidelines for that condition and returns tiered recommendations, each one with the guideline it came from. You then see the answers in your chat, which you can copy into your own notes. It can also just show you a full sample report so you can see the shape of the output before typing any numbers.
What you can do with it
- See a complete sample report in one click, no signup needed
- Check a handful of lab values quickly for a chosen condition
- Get guideline-cited recommendations for a set of made-up lab values
- List which biomarkers the engine scores, with units and reference ranges
- Read how the Phi Score is put together
- Flag tests that seem missing or overdue for a condition
Try asking your AI
- “Show me a sample Phi Longevity report so I can see what it looks like”
- “Here is a made-up panel for someone with type 2 diabetes: HbA1c 6.4, LDL-C 145, triglycerides 190. What does the guideline say?”
- “Which biomarkers does Phi Longevity score, and what units do they use?”
- “How is the Phi Score calculated?”
What it gives back to you
You get back a written report in your chat: a list of tiered recommendations, each with the clinical guideline it is based on, plus flags for anything that looks missing or overdue. It can also return a table of supported biomarkers with their units and normal ranges, and an explanation of the Phi Score. The output reads like a short clinical note you can skim and copy.
Before you start
What you need
- Nothing to install if you use the hosted link (https://philongevity.com/mcp) in a client that supports it
- Node.js 18 or newer if you want to run the small package on your own computer
- An MCP client such as Claude Desktop
- No account is required for the free tools; only made-up or de-identified values should be used
Good to know
Only send made-up or de-identified numbers; never paste real health records, because this public server is not a place for someone's private medical information, and one of the report tools is paid.
Install it with your AI
Add Phi Longevity 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 Phi Longevity 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 4,361 MCP servers here for you.
Who it's for
People helping someone manage a chronic condition, and health-focused agents, patient advocates, or care coordinators who want guideline-cited talking points rather than raw numbers.




