This server provides 50 tools for comprehensive plant genomics locus lookup over the Model Context Protocol, enabling AI agents to query and synthesize data across 23 public databases for 12 plant species (Arabidopsis, rice, maize, soybean, and more).
Gene & Locus Information
Fetch gene metadata from Ensembl Plants and Phytozome BioMart
Retrieve cross-database references (UniProt, NCBI Gene, TAIR, GO, etc.)
Get curated summaries, TAIR functional descriptions, and Araport11 computational descriptions via BAR/ThaleMine
Query genomic regions to list overlapping features (genes, transcripts, exons)
Sequence, Homology & Evolution
Retrieve genomic, CDS, cDNA, or protein sequences from Ensembl
Run NCBI BLAST searches (blastn/blastp/blastx/tblastn/tblastx) with async polling
Find orthologs/paralogs from Gramene Compara, OrthoDB ortholog groups, and PANTHER family classification
Generate consensus homologs by combining Gramene and BLAST results
Functional Annotation
GO annotations via QuickGO; plant-specific ontologies (PO/TO/PECO) from Planteome
KEGG pathway memberships and PlantCyc/PMN metabolic pathways (gene→enzyme→reactions)
GeneRIF curated functional statements with PubMed citations
GO/KEGG over-representation enrichment for gene lists via g:Profiler
Protein Structure & Domains
AlphaFold predicted structures with pLDDT confidence scores
Experimental PDB structures (X-ray/cryo-EM/NMR) ranked by coverage via PDBe
InterPro domain/family architecture (Pfam, CDD, PANTHER)
JASPAR transcription factor binding motifs with IUPAC consensus and position-frequency matrices
Interactions & Coexpression
STRING-DB interaction partners with per-channel confidence scores
Curated experimental interactions (BioGRID/IntAct) from ThaleMine
BAR AIV predicted interactions (Arabidopsis GRN / rice PPI)
ATTED-II coexpression neighbors with z-scores
Variation, GWAS & Expression
Natural variants overlapping a locus (EVA/dbSNP)
Variant consequence prediction via Ensembl VEP (SIFT/PolyPhen)
AraGWAS GWAS associations and 1001 Genomes natural variation (Arabidopsis-specific)
BAR eFP expression profiles across ~36 Arabidopsis ecotypes
Literature
Search Europe PMC for papers mentioning a locus, with abstracts, DOIs, and citation counts
Batch Processing
Batch variants (up to 50 loci per call) for Ensembl lookup, xrefs, UniProt, GO, homologs, pathways, interactions, coexpression, and more
Cross-Source Synthesis
gene_report: one-shot Markdown gene dossier composing 7 backends
analyze_locus_synth: locus overview combining Ensembl, UniProt, Europe PMC, and QuickGO
biological_context_synth: UniProt + Gramene + KEGG + STRING + ATTED-II with consensus partner ranking
find_homologs_synth: BLAST + UniProt enrichment in one call
consensus_homologs: cross-source homology deduped and scored
Organism input accepts canonical slugs, scientific names, common names, or NCBI taxids, with automatic routing to the relevant backend databases.
50 tools for plant-genomics locus lookup over the Model Context Protocol — 28 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, ThaleMine, and BAR (Bio-Analytic Resource for Plant Biology).
# Zero-install — uv fetches and runs it on demand
claude mcp add plant-genomics --scope local -- uvx plant-genomics-mcp# pipx — installs the CLI onto your PATH
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"Related MCP server: gwas-mcp
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.
50 tools across 23 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, ThaleMine, BAR.
28 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, EDAM ontology tags, and
behaviour annotations — every tool is readOnlyHint + openWorldHint, so
hosts can surface them without a destructive-action confirmation prompt.
# | Category | Tool | What it does |
1 | Gene metadata (live) |
| Fetches gene record from Ensembl Plants REST (any plant species). |
2 | Cross-references (live) |
| Fetches cross-DB references (UniProt, NCBI Gene, TAIR, GO, …) from Ensembl. |
3 | Gene metadata (live) |
| Fetches gene record from Phytozome BioMart (any Phytozome proteome). |
4 | Protein (live) |
| Resolves a locus to its UniProtKB record (Swiss-Prot preferred, TrEMBL OK). |
5 | Literature (live) |
| Searches Europe PMC for papers mentioning the locus (free, no API key). |
6 | GO annotations (live) |
| Fetches QuickGO GO annotations (locus → UniProt → QuickGO). |
7 | Sequence search (live) |
| NCBI BLAST URLAPI — async Put/Get polling with progress notifications. |
8 | Homology (live) |
| Fetches Gramene v69 homology entries (ortholog / paralog) with gene_tree_id. |
9 | Pathways (live) |
| Fetches KEGG pathway memberships. 7 organisms: Arabidopsis ( |
10 | Interactions (live) |
| Fetches STRING-DB first-neighbor interaction partners with per-channel score. |
11 | Coexpression (live) |
| Fetches ATTED-II Ath-u.c4-0 top-N coexpression neighbors with z-scores. |
12 | Curator summary (live) |
| Fetches BAR ThaleMine + GAIA-aliases curator summary for an Arabidopsis locus. |
13 | Expression (live) |
| Fetches BAR eFP-Browser expression profile (mean ± SD per tissue) for a locus. |
14 | Interactions (live) |
| Fetches BAR AIV interaction partners (Arabidopsis + rice) with confidence + papers. |
15 | Curator summary (live) |
| Silent upgrade — alias of |
16 | Metabolism (live) |
| Walks gene → enzyme → reactions → PlantCyc/PMN pathways (free BioCyc web-services API). The metabolic-pathway view KEGG/GO lack; found=false for non-enzymatic genes. 11 species have a PGDB. |
17 | Sequence (live) |
| Fetches a locus's sequence (genomic / cds / cdna / protein) from Ensembl |
18 | Region query (live) |
| Lists gene/transcript/cds/exon features overlapping a genomic interval (chr:start-end) via Ensembl |
19 | Enrichment (live) |
| GO + KEGG over-representation for a gene list via g:Profiler g:GOSt — "what is my DE / co-expression set enriched for?" Reports unmapped loci; optional custom background. All 12 organisms. |
20 | Plant ontology (live) |
| Plant Ontology (anatomy / dev-stage) + Trait Ontology annotations for a locus via Planteome (Solr) — the plant-specific ontologies GO doesn't cover. by_ontology rollup; taxon-filtered. Strong for 6 species. |
21 | Structure (live) |
| AlphaFold DB predicted 3D model for a locus (locus → UniProt → model): global mean pLDDT, per-band confidence, modelled span, and mmCIF / PDB / PAE URLs. found=false when no model is deposited. All 12 organisms. |
22 | Structure (live) |
| PDBe experimentally-solved (X-ray / cryo-EM / NMR) structures for a locus (locus → UniProt): best-first PDB id, chain, method, resolution, coverage, residue span. found=false when none deposited (common for plants). All 12 organisms. |
23 | Domains (live) |
| InterPro domain / family architecture (locus → UniProt): each entry's accession, name, type, source_database (Pfam included), integrated InterPro id, and residue spans, plus a count_by_type rollup. All 12 organisms. |
24 | TF motifs (live) |
| JASPAR curated TF DNA-binding profiles for a locus (locus → UniProt → symbol search, then UniProt-confirmed): matrix id, TF class/family, assay type (SELEX / ChIP-seq / PBM / DAP-seq), IUPAC consensus, PubMed refs, logo URL. Fuzzy name hits for other genes are quarantined in |
25 | TF motifs (live) |
| One JASPAR profile by matrix id (e.g. |
26 | Interactions (live) |
| ThaleMine CURATED EXPERIMENTAL interaction partners (BioGRID / IntAct / PSI-MI) for an Arabidopsis locus — per partner: detection method (two hybrid, pull down, ...), PSI-MI relationship type, physical vs genetic, source DB, PubMed IDs, and an evidence count. The experimental counterpart to |
27 | Function (live) |
| ThaleMine curated GeneRIF statements — one-sentence, manually curated descriptions of what the gene does, each tied to a PubMed ID (HY5 has 114). Citable functional context that GO terms and raw abstracts don't provide. Arabidopsis only. |
28 | Variation (live) |
| Natural (EVA/dbSNP) variants overlapping a locus's genomic span via Ensembl |
29 | Variation (live) |
| Ensembl VEP consequence prediction for a variant (region + allele, not locus) — most-severe consequence + per-transcript SO terms, IMPACT, SIFT/PolyPhen. All 12 organisms. |
30 | Orthology (live) |
| PANTHER protein family + subfamily (id + name), GO terms by aspect, protein class, and pathways. found=false when unclassified. All 12 organisms. |
31 | Orthology (live) |
| OrthoDB ortholog group (name, evolutionary rate) + cross-species member genes at the Viridiplantae level. organism_count + truncated. All 12 organisms. |
32 | Diversity (live) |
| AraGWAS genome-wide association hits per locus — score, MAF, SNP effect, phenotype/study. Arabidopsis-only. |
33 | Diversity (live) |
| 1001 Genomes natural-variation SNP effects across 1135 accessions — chr, position, effect, impact, amino-acid change, transcript + gene span. Arabidopsis-only. |
34 | Batch (live) |
| Parallel per-locus fanout for tools 1–6, 8–12, 14. Up to 50 loci per call. |
35 | Synthesis (live) |
| Compose 2–5 backends in parallel, return a |
36 | Synthesis (live) |
| One-shot "tell me about this gene" dossier — annotation + xrefs + protein + domains + GO + KEGG + STRING + literature composed into a rendered Markdown |
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/:
Walkthrough | Coverage |
One-shot Markdown gene dossier — 7 backends composed, with graceful KEGG degradation. | |
Ensembl → xrefs → UniProt → Europe PMC → QuickGO chain (5 tools). | |
BLAST + per-hit UniProt enrichment. | |
Gramene + KEGG + UniProt + STRING + ATTED-II (5 tools). | |
All 4 v0.8 synthesis tools ( | |
v0.9 multi-organism resolver against rice + maize — per-backend routing on PyPI v1.0.4. |
Clients discover them via resources/list and prompts/list.
Resources (resources/read):
URI | What |
| Per-backend |
| Slug → Phytozome |
| Per-backend liveness rollup — |
| Markdown table of all 12 supported plants × 9 ID slots (ncbi_taxid / ensembl / phytozome / string / europe_pmc / kegg / atted / gprofiler / plantcyc). |
Prompts (prompts/get):
Name | Required | Optional | Chains |
|
|
| Ensembl → xrefs → UniProt → Europe PMC → QuickGO. |
|
|
|
|
|
|
| Gramene → KEGG → UniProt → STRING → ATTED-II. |
Transport | How to launch |
stdio (default) |
|
streamable-HTTP |
|
The HTTP transport is stateless and emits JSON responses by default — the right shape for registry indexers and remote hosting.
A small personal demo runs at:
https://mjarnoldgt76.tail86d19d.ts.net/mcpIntended 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/mcpFor 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.
Stdio needs no configuration. The two env vars that matter:
Variable | When | Effect |
| HTTP transport only | Bearer token for |
| If you use BLAST | NCBI etiquette contact. Unset → placeholder + per-call warning; NCBI may throttle. |
Variable | Default | Effect |
|
| HTTP bind address. |
|
| HTTP TCP port. |
|
| Reject POSTs with |
|
|
|
|
|
|
|
| Max in-flight BLAST searches per process (NCBI per-IP rate limit). |
|
| Per-backend TTL+LRU cache entry lifetime, in seconds. 200-only. |
|
| Max entries per backend before LRU eviction. |
| unset | Any non-empty value makes every cache a no-op. |
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.
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:
Wire prefix | When |
| 404 / empty BioMart row / invalid locus identifier |
| 429 retry budget exhausted — back off and retry |
| 5xx past retry budget — service outage, try a peer backend |
| Other (BioMart |
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.
.venv/bin/pip install -e '.[dev]' # or: uv sync --extra 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 .With uv, pass --extra dev — a bare uv sync omits (and removes) the test
dependencies. See CONTRIBUTING.md.
CI runs the unit suite + the stdio smoke on every push/PR (matrix:
Python 3.11, 3.12, 3.13, 3.14 — the full requires-python range). 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.
Listed in the official MCP registry
under the namespace below (ownership-verification token for mcp-publisher):
mcp-name: io.github.musharna/plant-genomics-mcpMIT — see LICENSE. Underlying services (Ensembl Plants,
Phytozome, TAIR, PlantCyc, BAR) have their own terms of use; consult
each before bulk querying.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MyGene.info — gene annotation joining NCBI/Ensembl/UniProt/KEGG/OMIM
STRING protein-protein interaction networks across ~12k organisms
MCP gateway federating 21 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/musharna/plant-genomics-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server