Skip to main content
Glama
w0lph

dog-geroscience-mcp

by w0lph
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

k9 — AI tooling for canine longevity research

Research brief: canine-longevity-ai-opportunities.md (landscape, ranked opportunities, and the Phase 1 plan in Section 7).

Phase 1 components:

Directory

What

Status

corpus/

canine-aging-corpus: reproducible Europe PMC corpus of the canine aging literature (records, JATS→Markdown full text from Europe PMC or NCBI, manifest, version file).

Complete: 3,565 records (2,185 core); full text for 1,140 of 1,347 PMCIDs (the other 207 are publisher-restricted from XML distribution).

mcp/

dog-geroscience-mcp: MCP server with 17 dog-specific aging tools (AnAge/DrugAge/GenAge dog rows, dog orthologs via Ensembl with caching, FDA Km dose translation, Dog Aging Project codebooks across 9 releases, NIH RePORTER, BM25 corpus search with full-text retrieval, FOI summaries and structured records, intervention dossier).

Complete: 23 offline tests, smoke-tested against live Ensembl/RePORTER and over stdio; DB built from the finished corpus and FOI layers.

questions/

canine-geroscience-questions: 133 questions across 10 categories, each with a gold answer and a verbatim quote from a corpus record, enforced by a validator; plus a BM25 retrieval baseline.

v0.1: drafted, validator-clean, then reviewed item-by-item by an independent LLM pass (9 fixes, 1 drop); recall@5 = 0.985. No domain-expert review yet.

Phase 2 components:

Directory

What

Status

foi/

foi-summaries: FDA CVM Freedom of Information summaries as a public-domain dataset (index of 1,726 summaries, 497 dog-product PDFs, text, parsed sections and General Information fields, species flags) plus a typed, quote-validated extraction of all 497 summaries (1,026 PK values, 193 safety studies, 414 effectiveness studies, 918 adverse-reaction rows).

Complete: 497 records, 97% with parsed sections; structured layer covers all 497 (4,510 quotes, 0 errors, 79 explained warnings).

mcp/ (extended)

intervention_dossier (synonym-aware, species-filtered), foi_summary_search, foi_summary_get, foi_structured_search, the dossier_briefing prompt; scripts/dossier_eval.py coverage table over ITP compounds.

Complete; 23 tests.

.\rebuild.ps1 regenerates everything in dependency order (-Fresh re-fetches sources). PUBLISHING.md is the step-by-step for the Hugging Face Hub (dataset cards and staging script in publish/), PyPI and the MCP registry (mcp/server.json), and Glama (glama.json, root Dockerfile). Once published, the server installs with uvx dog-geroscience-mcp and downloads its database on first run. Each directory is its own uv project:

cd corpus && uv sync --extra dev && uv run pytest -q
cd mcp && uv sync && uv run dog-geroscience-mcp build && uv run pytest -q
cd questions && uv sync && uv run pytest -q && uv run cgq validate data/canine_geroscience_v0.jsonl --require-ids
cd foi && uv sync && uv run foi run && uv run pytest -q
cd mcp && uv run dog-geroscience-mcp build --skip-download   # picks up ../foi/data/foi_summaries_dog.jsonl

Large derived data (corpus/data, mcp/data, FOI PDFs and text) is git-ignored; it is rebuilt by the pipelines and published as Hugging Face datasets (publish/).

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Resources

Related MCP Connectors

Related MCP Servers

  • data-aggregator-mcp

    musharna
    A
    license
    A
    quality
    A
    maintenance
    Searches and fetches research datasets across Zenodo, DataCite (Dryad/Figshare/Dataverse/OSF), NCBI omics archives (GEO/SRA/BioProject), and the literature (PubMed/OpenAIRE) through one normalized model — deduplicating by DOI, expanding organism queries with NCBI Taxonomy synonyms, and bridging papers to the datasets they produced. Resolves citations and open-access full text, and downloads files.
    6
    310 PyPI
    4
    MIT

  • BioMCP

    gucci10248
    A
    license
    Not graded
    quality
    A
    maintenance
    Read-only biomedical MCP server connecting PubMed, ClinicalTrials.gov, ClinVar, gnomAD, OncoKB, Reactome, KEGG, UniProt, PharmGKB, CPIC, OpenFDA, Monarch Initiative, GWAS Catalog, and more. One command grammar for all biomedical entities — genes, variants, diseases, drugs, trials, articles, phenotypes, pathways, proteins, diagnostics, and adverse events. 27 tools. Apache-2.0 license.
    1
    Apache 2.0
  • sniff-mcp by Sniffscore

    sniff-mcpofficial

    Sniffscore
    A
    license
    Not graded
    quality
    D
    maintenance
    Agent-callable canine genomics API providing breed-stratified allele frequencies, pathogenicity predictions, and variant-gene-breed-disease knowledge graph for dog DNA.
    MIT