convez.ai
MCP ServerBusca & PesquisaAvançado
musharna

Plant Genomics MCP

musharna/plant-genomics-mcp

32 ferramentas de genômica vegetal via MCP — 11 bases integradas

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP especializado em genômica vegetal com 32 ferramentas integradas a 11 bases de dados públicas (Ensembl Plants, Phytozome, UniProt, QuickGO, NCBI BLAST, KEGG, STRING-DB e outras). Oferece buscas de locus, anotações gênicas, vias metabólicas e síntese de dados cross-fonte para pesquisa em biologia de plantas.

Instalação

$npx convez-ai musharna/plant-genomics-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
8
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 4 dias
Versão
v1.32.0
Issues abertas
3
Contribuidores
3

Casos de uso

  • Pesquisa em biologia e genômica de plantas
  • Busca de anotações gênicas e metadados de locus
  • Análise de vias metabólicas e interações proteína-proteína
  • Síntese de dados de múltiplas fontes públicas para estudos comparativos

Veredito

Ferramenta robusta e bem-mantida para pesquisadores em genômica vegetal que precisam integrar múltiplas bases de dados. Cobertura abrangente de organismos vegetais e documentação clara, mas demanda conhecimento em genômica para máxima utilidade.

README

A tradução para o português deste README ainda está na fila.

🌱 plant-genomics-mcp

32 tools for plant-genomics locus lookup over the Model Context Protocol — 16 single-locus + 12 parallel-batch + 4 cross-source synthesis variants. Free, public sources: Ensembl Plants, Phytozome BioMart, UniProtKB, Europe PMC, QuickGO, NCBI BLAST, Gramene, KEGG, STRING-DB, ATTED-II, and BAR (Bio-Analytic Resource for Plant Biology).

PyPI CI Docker Python License Glama

📦 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"

🛠️ Tools

32 tools across 11 backends — Ensembl Plants, Phytozome BioMart, UniProtKB, Europe PMC, QuickGO, NCBI BLAST, Gramene, KEGG, STRING-DB, ATTED-II, BAR. 16 single-locus + 12 parallel-batch + 4 cross-source synthesis. All 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.

#CategoryToolWhat it does
1Gene metadata (live)ensembl_plants_lookup_locusFetches gene record from Ensembl Plants REST (any plant species).
2Cross-references (live)get_gene_xrefsFetches cross-DB references (UniProt, NCBI Gene, TAIR, GO, …) from Ensembl.
3Gene metadata (live)phytozome_lookup_locusFetches gene record from Phytozome BioMart (any Phytozome proteome).
4Protein (live)resolve_locus_to_uniprotResolves a locus to its UniProtKB record (Swiss-Prot preferred, TrEMBL OK).
5Literature (live)locus_literatureSearches Europe PMC for papers mentioning the locus (free, no API key).
6GO annotations (live)locus_go_annotationsFetches QuickGO GO annotations (locus → UniProt → QuickGO).
7Sequence search (live)blast_sequenceNCBI BLAST URLAPI — async Put/Get polling with progress notifications.
8Homology (live)gramene_homologsFetches Gramene v69 homology entries (ortholog / paralog) with gene_tree_id.
9Pathways (live)kegg_pathwaysFetches KEGG pathway memberships. 7 organisms: Arabidopsis (ath:, native AGI), + rice (osa:), maize (zma:), soybean (gmx:), barley (hvg:), poplar (pop:), brachypodium (bdi:) bridged via Ensembl → Entrez ID.
10Interactions (live)string_interactionsFetches STRING-DB first-neighbor interaction partners with per-channel score.
11Coexpression (live)atted_coexpressionFetches ATTED-II Ath-u.c4-0 top-N coexpression neighbors with z-scores.
12Curator summary (live)bar_gene_summaryFetches BAR ThaleMine + GAIA-aliases curator summary for an Arabidopsis locus.
13Expression (live)bar_efp_expressionFetches BAR eFP-Browser expression profile (mean ± SD per tissue) for a locus.
14Interactions (live)bar_aiv_interactionsFetches BAR AIV interaction partners (Arabidopsis + rice) with confidence + papers.
15Curator summary (live)tair_locus_infoSilent upgrade — alias of bar_gene_summary. MCP tool name preserved for clients.
16Subscription redirectplantcyc_locus_infoReturns subscription notice + redirect to live backends. No upstream call.
17Batch (live)batch_* (twelve variants)Parallel per-locus fanout for tools 1–6, 8–12, 14. Up to 50 loci per call.
18Synthesis (live)*_synth / consensus_homologs (four)Compose 2–5 backends in parallel, return a SynthesisEnvelope with per-step status.

⚡ 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/:

WalkthroughCoverage
analyze_locus_AT1G01010.mdEnsembl → xrefs → UniProt → Europe PMC → QuickGO chain (5 tools).
find_homologs_AT1G01010_NAC_domain.mdBLAST + per-hit UniProt enrichment.
biological_context_AT1G01010.mdGramene + KEGG + UniProt + STRING + ATTED-II (5 tools).
v0.8_synthesis_walkthrough.mdAll 4 v0.8 synthesis tools (*_synth + consensus_homologs) on the same locus.
cross_organism_walkthrough.mdv0.9 multi-organism resolver against rice + maize — per-backend routing on PyPI v1.0.4.

📚 Resources & prompts

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

Resources (resources/read):

URIWhat
pgmcp://cache/statsPer-backend TTLCache rollup — {hits, misses, size} for each live backend.
pgmcp://organisms/phytozomeSlug → Phytozome organism_id map.
pgmcp://backends/statusPer-backend liveness rollup — name, base_url, kind, subscription_gated, probed_at.
pgmcp://organisms/coverageMarkdown table of all 12 supported plants × 5 ID slots (ncbi_taxid / ensembl / phytozome / …).

Prompts (prompts/get):

NameRequiredOptionalChains
analyze_locuslocusorganism (default arabidopsis_thaliana)Ensembl → xrefs → UniProt → Europe PMC → QuickGO.
find_homologssequenceprogram (default blastp)blast_sequence → per-hit resolve_locus_to_uniprot for UniProt-shaped accessions.
biological_contextlocustop_n (default 10)Gramene → KEGG → UniProt → STRING → ATTED-II.

🔌 Transports

TransportHow to launch
stdio (default)plant-genomics-mcp (after install) or via Docker above
streamable-HTTPplant-genomics-mcp-http — POST JSON-RPC at http://host:port/mcp

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:

VariableWhenEffect
PLANT_GENOMICS_MCP_HTTP_TOKENHTTP transport onlyBearer token for /mcp; must be ≥32 chars or the HTTP server aborts at startup. Generate openssl rand -hex 32.
PLANT_GENOMICS_MCP_NCBI_EMAILIf you use BLASTNCBI etiquette contact. Unset → placeholder + per-call warning; NCBI may throttle.
VariableDefaultEffect
PLANT_GENOMICS_MCP_HTTP_HOST127.0.0.1HTTP bind address.
PLANT_GENOMICS_MCP_HTTP_PORT8765HTTP TCP port.
PLANT_GENOMICS_MCP_HTTP_MAX_BODY2097152 (2 MiB)Reject POSTs with Content-Length larger than this.
PLANT_GENOMICS_MCP_HTTP_STATELESS10 keeps per-client session state (SSE-style).
PLANT_GENOMICS_MCP_HTTP_JSON10 switches the response shape to streaming SSE events.
PLANT_GENOMICS_MCP_BLAST_CONCURRENCY2Max in-flight BLAST searches per process (NCBI per-IP rate limit).
PLANT_GENOMICS_MCP_CACHE_TTL600Per-backend TTL+LRU cache entry lifetime, in seconds. 200-only.
PLANT_GENOMICS_MCP_CACHE_SIZE256Max entries per backend before LRU eviction.
PLANT_GENOMICS_MCP_CACHE_DISABLEDunsetAny 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.

⚠️ 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:

Wire prefixWhen
[NotFoundError]404 / empty BioMart row / invalid locus identifier
[RateLimitError]429 retry budget exhausted — back off and retry
[UpstreamUnavailableError]5xx past retry budget — service outage, try a peer backend
[PlantGenomicsError]Other (BioMart Query ERROR: body, unexpected column count, etc.)

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.

Ver o original no GitHub

Bom para

Relacionados