smaniches/alphafold-sovereign-mcp

Answering a structural-biology or variant question usually means querying
many public databases by hand — AlphaFold DB, Open Targets, ClinVar,
gnomAD, and more — and reconciling their formats. This server wraps those
sources behind one set of MCP tool calls that run as a local process on
your own machine, with no hosted service of ours in the path, no
telemetry, and a local SQLite knowledge graph that never leaves your disk.
In the default online mode the tools query those public upstreams
directly, so the identifiers you look up are sent to them (and one,
DisGeNET, needs its own free API key); set ALPHAFOLD_OFFLINE=1 to refuse
outbound requests before any socket opens, so no identifier leaves the
machine (the knowledge-graph tools still answer from local data; the
upstream tools report their source as unavailable). "Sovereign" here means
local-first — your compute and stored results stay on your machine — not
that the server runs without a network.
A Model Context Protocol server — an AlphaFold MCP server — that
wraps AlphaFold DB and 8 other public biomedical data sources behind
a set of MCP tool calls, with a conditional UniProtKB request to verify
explicitly requested displayed isoforms. It is backed by a local SQLite
knowledge graph with query and export tools (results can be persisted through its API;
automatic per-invocation persistence is not yet wired).
This is an unfunded, independent open-source project. It is not a
service, not certified for any regulated use, and its outputs are
research aids that should be reviewed by qualified humans before any
clinical or regulatory use.
**Research authorship:** Santiago Maniches (ORCID 0009-0005-6480-1987) independently directs and maintains this server and is the sole scientific author of its original research contributions. AI-assisted tools have supported coding, testing, and internal review. They are not scientific coauthors, clinical validators, or a substitute for independent evaluation. The public databases, prediction models, and existing algorithms remain credited to their sources.
This project is not affiliated with, endorsed by, or sponsored by
Google DeepMind or EMBL-EBI. "AlphaFold" is a trademark of its
respective owner and is used here only to describe the public data
(the AlphaFold DB API) that this software consumes.
**Status:** Beta. Engineering-validated (100% line and branch
coverage). Not yet scientifically validated by
independent domain experts; not yet deployed in production. See
STATUS.md and LIMITATIONS.md.
---
What this is
A Python MCP server that:
- Wraps AlphaFold DB, MONDO, HPO, Open Targets, ClinVar, gnomAD,
DisGeNET, ChEMBL, and Ensembl behind MCP tool calls. Explicit numbered
isoforms may also trigger a UniProtKB sequence-and-identity check. Each call
is a thin orchestration over those upstreams; the server does not
add scientific judgement.
- Composes upstreams into multi-source workflows: variant
cross-reference reports, disease–target landscape summaries,
heuristic target-druggability scoring, drug-repurposing candidate
ranking, and cross-species structural-distance computation.
- Ships a local SQLite knowledge graph (storage/knowledge_graph.py)
with query, export, and traversal tools. It loads a curated boot
seed automatically when empty (storage/seed.py, 16 entities and 15
relationships; disable with AFSMCP_DISABLE_KG_SEED=1) and can be
extended by writing through the knowledge-graph API. There is no
automatic per-invocation persistence: the analysis tools do not write
to the store on their own.
- Includes a topological-data-analysis (TDA) module that computes
persistent-homology fingerprints (Betti numbers β₀, β₁, β₂) over
Vietoris-Rips filtrations of Cα coordinates, and an
L2-distance comparator between those fingerprint vectors. The full
persistent-homology features require the optional [tda] extra
(gudhi).
It targets mcp-spec 2025-06-18 and runs on Python 3.10–3.13.
**AlphaFold DB compatibility:** the prediction API announced modern model
and sequence field names and a legacy-field sunset in June 2026.
The sampled live API still exposes old aliases as of 9 October 2026.
The client uses the current fields, retains legacy-response compatibility, and
selects the exact requested UniProt accession when the API returns