mgi-link
An MCP server that provides mouse genetics data from Mouse Genome Informatics (MGI), enabling LLM agents to query markers, mutations, alleles, phenotypes, and disease models.
README
mgi-link
An MCP (Model Context Protocol) / API server that grounds mouse-genetics work in Mouse Genome Informatics (MGI, informatics.jax.org). It reproduces the data on an MGI gene/marker page — especially Mutations, Alleles, and Phenotypes — for LLM agents.
mgi-link is a sibling of hgnc-link, gnomad-link, uniprot-link, and
gencc-link and shares their architecture: a local SQLite index built from the
MGI bulk reports, refreshed by cron, served over a structured MCP surface.
Why
The MGI gene page (e.g. Wt1, MGI:98968)
is a rich JS app with no clean JSON API. mgi-link rebuilds that surface from
MGI's canonical bulk data reports into a fast, offline, deterministic index and
exposes it as MCP tools with structured outputs, response-mode verbosity
control, and _meta.next_commands chaining.
Tools
| Tool | Purpose |
|---|---|
resolve_marker |
Resolve a mouse symbol / MGI id / human ortholog → canonical marker |
get_marker |
Full marker record: location, xrefs, ortholog, summary counts |
search_markers |
FTS over marker symbol / name / synonyms |
get_marker_alleles |
Mutations & Alleles + generation-method category counts |
get_marker_phenotypes |
MP annotations (allelic composition, background, PubMed) + summary |
get_phenotype_overview |
The 27-system Phenotype Overview grid |
get_marker_diseases |
Human-mouse disease models (DO/OMIM) |
get_marker_ortholog |
Mouse ↔ human ortholog (HGNC/Entrez/Ensembl/OMIM) |
get_mp_term |
Mammalian Phenotype ontology term (parents/children/systems) |
search_phenotype_terms |
FTS over MP terms |
find_markers_by_phenotype |
Reverse: MP term → mouse genes (descendants included) |
get_server_capabilities, get_mgi_diagnostics |
Discovery |
Data sources
The local index is built from the MGI bulk reports at
https://www.informatics.jax.org/downloads/reports/:
MRK_List2, MGI_PhenotypicAllele, MGI_GenePheno, VOC_MammalianPhenotype,
MPheno_OBO.ontology, HOM_MouseHumanSequence, MGI_DO (+ MRK_ENSEMBL).
A live MouseMine (InterMine) enrichment client is reserved for v2.
Quick start
make install # uv sync --group dev
make data # download the MGI reports and build the local SQLite index
make dev # run the unified server (FastAPI /health + MCP /mcp)
make mcp-serve # run the stdio MCP server
make test # run the test suite
Register with Claude:
claude mcp add mgi-link -- uv run mgi-link-mcp
Data & license
MGI data are freely available for research use; please cite MGI / The Jackson Laboratory. The Mammalian Phenotype Ontology is licensed CC BY 4.0. Research use only; not for clinical decision support, diagnosis, treatment, or patient management.
Development
make ci-local is the definition-of-done gate (format-check, lint, 500-line
budget, mypy strict, tests). See AGENTS.md for engineering conventions and
docs/ for architecture and deployment.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.