MCP server · Research
AlphaFold Sovereign MCP server
by smaniches
Lets your AI look up protein structures, variants, diseases and drug targets from public biology databases.
This is a helper program that connects your AI to a set of public biology databases, such as AlphaFold DB, ClinVar, gnomAD and Open Targets. It runs on your own computer and keeps a small local database of what you look up. It is handy for anyone who works with proteins, genes or variants and wants quick answers without hopping between many websites.
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 an app or service. This one connects your AI to public biomedical databases like AlphaFold DB and ClinVar. So when you ask a question about a protein or a variant, your AI can look things up there and bring the answers back to you.
What this MCP server does
You ask your AI a question, for example about a gene variant or a protein. Your AI uses this helper to send the right lookups to public databases such as AlphaFold DB, ClinVar, gnomAD and Open Targets. The helper gathers the answers, lines them up and stores a copy in a small local database on your machine. Then your AI shows you a summary in the chat, and you can ask follow-up questions or export the results.
Click to zoomWhat you can do with it
- Look up a protein structure and its confidence score
- Check what is known about a gene variant in ClinVar and gnomAD
- Find drug targets linked to a disease
- Compare the shapes of proteins across species
- Get a phenotype profile for a gene
- Search a local knowledge graph of your past lookups
- Export your results as a file for further analysis
Try asking your AI
- “Triage BRCA1 c.5266dupC”
- “Assess EGFR as a drug target”
- “What diseases are linked to the ACE2 gene”
- “Compare the structure of human ACE2 with the mouse version”
What it gives back to you
You get back clear answers in the chat: lists of diseases, variant details, confidence scores, drug candidates, or short summaries. Some tools also return structured data you can export as a file. The local knowledge graph tools let you search and revisit earlier results. Everything is shown as text or tables you can read and copy.
Before you start
What you need
- Python 3.10 or newer
- An internet connection for the online mode (some sources need it)
- A free DisGeNET API key if you want to use that source
- The Claude desktop app or another MCP-compatible AI client
Good to know
The results are research aids, not medical advice, and the structure predictions and drug-target scores should be checked by a qualified person before any clinical or regulatory use.
Install it with your AI
Add AlphaFold Sovereign 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 AlphaFold Sovereign 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
Researchers, students and analysts who work with proteins, genes or variants and want quick answers without visiting many websites.
