🌱 plant-genomics-mcp

48 tools for plant-genomics locus lookup over the Model Context Protocol — 26 single-locus + 1 motif lookup + 1 region query + 1 variant annotator + 1 gene-set enrichment + 1 BLAST search + 12 parallel-batch + 5 cross-source synthesis variants. Free, public sources: Ensembl Plants, Phytozome BioMart, UniProtKB, Europe PMC, QuickGO, Planteome, PlantCyc/PMN, g:Profiler, NCBI BLAST, Gramene, JASPAR, KEGG, STRING-DB, ATTED-II, and BAR (Bio-Analytic Resource for Plant Biology).

📦 Install

pipx install plant-genomics-mcp
claude mcp add plant-genomics --scope local -- plant-genomics-mcp

# GHCR Docker image
docker pull ghcr.io/musharna/plant-genomics-mcp:latest
claude mcp add plant-genomics --scope local -- \
  docker run --rm -i ghcr.io/musharna/plant-genomics-mcp:latest

# From source
git clone https://github.com/musharna/plant-genomics-mcp.git
cd plant-genomics-mcp
python -m venv .venv && .venv/bin/pip install -e .
claude mcp add plant-genomics --scope local -- "$(pwd)/.venv/bin/plant-genomics-mcp"

💬 Try it

Once connected, ask Claude a plain-language question — you don't have to name any tool or remember the chain:

"Tell me everything about the Arabidopsis gene AT1G01010 — its function, GO terms, KEGG pathways, protein-interaction partners, and recent papers."

Claude fans out across Ensembl Plants, UniProt, QuickGO, KEGG, STRING-DB, and Europe PMC in a single turn and hands back one synthesized answer. Swap in any locus and pass organism= for cross-species — e.g. rice Os01g0100100 (oryza_sativa) — and it routes to the right backends automatically.

🛠️ Tools

48 tools across 22 backends — Ensembl Plants, Phytozome BioMart, UniProtKB, Europe PMC, QuickGO, Planteome, PlantCyc/PMN, g:Profiler, AlphaFold DB, PDBe, InterPro, JASPAR, PANTHER, OrthoDB, AraGWAS, 1001 Genomes, NCBI BLAST, Gramene, KEGG, STRING-DB, ATTED-II, BAR. 26 single-locus + 1 motif lookup + 1 region query + 1 variant annotator + 1 gene-set enrichment + 1 BLAST search + 12 parallel-batch + 5 cross-source synthesis. Most take a TAIR-style locus (e.g. AT1G01010) plus optional organism= (slug / scientific name / common name / NCBI taxid — 12-plant curated coverage matrix at the pgmcp://organisms/coverage MCP resource). All publish JSON outputSchema and EDAM ontology tags.

⚡ Quickstart

After install, the simplest call returns the Ensembl Plants record for NAC001 — the canonical worked example used throughout examples/:

// arguments
{ "locus": "AT1G01010" }

// result (truncated)
{
  "id": "AT1G01010",
  "organism": "arabidopsis_thaliana",
  "display_name": "NAC001",
  "biotype": "protein_coding",
  "seq_region_name": "1",
  "start": 3631,
  "end": 5899,
  "strand": 1,
  "assembly_name": "TAIR10",
  "description": "NAC domain containing protein 1 ..."
}

Cross-species — pass organism=:

{ "locus": "Os01g0100100", "organism": "oryza_sativa" }

In Claude Code, the same prompt fans out across Ensembl, UniProtKB, and Europe PMC in a single turn (animated demo):

Full per-tool walkthroughs (with real upstream-API transcripts) live in examples/:

📚 Resources & prompts

Clients discover them via resources/list and prompts/list.

Resources (resources/read):

Prompts (prompts/get):

🔌 Transports

The HTTP transport is stateless and emits JSON responses by default — the right shape for registry indexers and remote hosting.

Hosted endpoint

A small personal demo runs at:

https://mjarnoldgt76.tail86d19d.ts.net/mcp

Intended for registry indexers, one-off evaluation, and quick interactive testing — not for production workloads. No SLA, no uptime commitment, URL may change without notice (single laptop on a residential connection).

# liveness probe
curl https://mjarnoldgt76.tail86d19d.ts.net/healthz
# {"status":"ok"}

# connect from Claude Code
claude mcp add --transport http plant-genomics-mcp \
  https://mjarnoldgt76.tail86d19d.ts.net/mcp

For anything beyond casual evaluation, self-host. The HTTP transport is the same binary; self-hosting buys deterministic uptime, your own bearer-token gate (PLANT_GENOMICS_MCP_HTTP_TOKEN), and NCBI BLAST etiquette under your own contact email.

⚙️ Configuration

Stdio needs no configuration. The two env vars that matter:

The cache is process-local — restart the server to drop all entries. Long-running calls (retry storms, multi-second Phytozome BioMart POSTs) emit MCP notifications/progress over the active session; clients opt in via progressToken in the request _meta.

⚠️ Error model

All live tools raise PlantGenomicsError subclasses; the MCP SDK stringifies them into the wire content with a [ClassName] prefix so clients can route on failure kind without parsing the message:

Batch tools return {tool, count, results, errors} where results[locus] is the same shape as the single-locus tool and errors[locus] is the same [ClassName] message string. Ensembl's batch uses the native POST /lookup/id endpoint (one HTTP round-trip); everything else fans out via asyncio.gather.

🧪 Development

.venv/bin/pip install -e '.[dev]'
.venv/bin/pytest -q                                       # unit tests
PLANT_GENOMICS_MCP_LIVE=1 .venv/bin/pytest -q             # adds live network probes
PLANT_GENOMICS_MCP_STDIO_SMOKE=1 .venv/bin/pytest -q      # adds stdio smoke
.venv/bin/ruff check .

CI runs the unit suite + the stdio smoke on every push/PR (matrix: Python 3.11, 3.12). The live-network gate is not run in CI to avoid flakes from upstream availability.

Scientific validation / drift detection. scripts/benchmark_annotations.py drives a curated corpus of canonical loci (27, spanning all 12 organisms) through every backend + synthesis pipeline and compares results to a frozen baseline, emitting PASS / DRIFT / FAIL plus cross-source consistency invariants. It's how upstream data drift is caught. A scheduled GitHub Actions workflow (.github/workflows/benchmark.yml) runs it weekly and pages on a confirmed regression. Operator guide: docs/benchmarking.md.

.venv/bin/python scripts/benchmark_annotations.py        # full live sweep (~3-5 min)

See CHANGELOG.md for release notes, including the v0.8 → v0.9 species=/organism_id= → organism= migration and the v1.0.1 HTTP-token enforcement change.

MCP registry

Listed in the official MCP registry under the namespace below (ownership-verification token for mcp-publisher):

mcp-name: io.github.musharna/plant-genomics-mcp

License

MIT — see LICENSE. Underlying services (Ensembl Plants, Phytozome, TAIR, PlantCyc, BAR) have their own terms of use; consult each before bulk querying.