plant-genomics-mcp
An MCP server that lets AI agents look up plant genes across 24 free public databases, with 58 read-only tools covering gene records, sequence, protein/structure, function, pathways, interactions, homology, variation, and one-call synthesis reports for 12 curated plants.
Gene records & cross-references — Ensembl Plants, Phytozome, TAIR/BAR, MaizeGDB v4↔v5 translation, and cross-DB ID rollups (UniProt, NCBI Gene, etc.).
Sequence & search — fetch genomic/CDS/cDNA/protein sequences and run NCBI BLAST (blastn/p/blastx/tblastn/tblastx).
Protein & structure — resolve loci to UniProt, batch ID mapping, InterPro/Pfam/PANTHER domains, AlphaFold predictions, and PDBe experimental structures.
Function & literature — GO annotations (QuickGO), Plant Ontology/Trait Ontology (Planteome), GeneRIFs, GO/KEGG enrichment for gene lists, and Europe PMC literature search.
Pathways — KEGG and PlantCyc metabolic pathway memberships.
Interactions & expression — STRING networks, curated experimental interactions (ThaleMine), BAR AIV, ATTED-II coexpression, and BAR eFP ecotype expression.
Homology & families — Gramene orthologs/paralogs, Ensembl Compara paralogs and gene-tree members, OrthoDB groups, PANTHER families, and reverse entry→members lookup.
TF motifs & variation — JASPAR binding profiles/matrices, Ensembl variants, VEP consequence prediction, AraGWAS hits, and 1001 Genomes natural variation.
Regions & assemblies — list features in a genomic interval and inspect an organism's assembly/seq-regions.
Batch & synthesis — batch fan-out over up to 50 loci (dedicated
batch_*tools plusbatch_locus_callfor any locus tool), and multi-source orchestrators (gene_report,analyze_locus_synth,find_homologs_synth,biological_context_synth,consensus_homologs). Note: many tools are Arabidopsis-only or limited to specific species (e.g. ThaleMine, AraGWAS, ATTED-II), and organism coverage varies by backend.
plant-genomics-mcp
plant-genomics-mcp is an MCP server that lets AI agents look up plant genes in 24 free public databases, from Ensembl Plants and UniProt to KEGG, STRING and AlphaFold, with curated coverage of 12 plants.
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: hgnc-link
Try it
Ask in plain language; the client picks the tools:
"Tell me everything about the Arabidopsis gene AT1G01010 — its function, GO terms, KEGG pathways, protein-interaction partners, and recent papers."
For another species, name it or pass organism= (e.g. rice Os01g0100100,
oryza_sativa). A recorded ortholog run, where Claude checked three sources
and said which one does not back the rice match:
Prompts and full answers for both screenshots: examples/assets/cards/RUN.md.
A worked 64-call run over 114 genes in three organisms, with the 51 gaps it logged (39 since closed),
is in examples/arf_family/PAGE.md. Per-tool walkthroughs, including
the one-call gene dossier gene_report_AT1G01010.md, are in
examples/.
What the benchmark shows
Claude with the server was compared with Claude using web search. On 36 multi-step gene questions, 3 runs each, Haiku 5.5 got 31 right in every run with the server and 9 with web search: a pre-registered win (Holm-adjusted McNemar p = 2.1e-5), at 0.07 times the cost. Sonnet 5.5 tied (35 and 35; 0.65× the time, 1.49× the cost). With Opus 5.5 (the re-run 2026-10-18) both got all 108 right; the server was faster at the median (0.77×, 95% CI 0.64 to 0.96) and dearer (1.72×, 1.46 to 2.24). On a harder task, 25 maize v4 gene IDs to v5 genes and every UniProt accession (10 held-out questions, Sonnet 5.5), the server got 10 right and web search 0, declining each (sign test p = 0.002; results).
The chart: Opus 5.5 on 52 plant gene-lookup questions, 151 of 156 right with web search and 156 of 156 with the server, not separated (McNemar p = 0.125). The key comes from the databases the server reads, so this tests the lookups, not whether the databases are right. We wrote the questions; an outside re-run is welcome. Method; Haiku and Sonnet.
Tools
58 tools across 24 backends:
Area | Tools |
Gene records |
|
Sequence |
|
Protein and structure |
|
Function |
|
Pathways |
|
Interactions and expression |
|
Homology and families |
|
TF motifs |
|
Variation |
|
Regions and assemblies |
|
Provenance |
|
Batch and synthesis |
|
Most take a locus (e.g. AT1G01010) and an optional organism=. Every tool is
marked read-only. What each tool does, the list of backends, the MCP resources
and prompts, all environment variables and the error model:
docs/reference.md.
Configuration
stdio (plant-genomics-mcp, the default) needs no configuration.
plant-genomics-mcp-http serves streamable HTTP at http://host:port/mcp;
there is no public endpoint, so you run it yourself, behind your own token.
Variable | When | Effect |
| HTTP transport only | Bearer token for |
| If you use BLAST | NCBI etiquette contact. Unset → placeholder + per-call warning; NCBI may throttle. |
Development
.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 .A bare uv sync omits the test dependencies. CI runs the unit suite and the
stdio smoke on Python 3.11–3.14 with the network blocked. A weekly job checks
27 loci against a frozen snapshot and pages on drift
(docs/benchmarking.md). Setup: CONTRIBUTING.md.
Release notes: CHANGELOG.md.
License
MIT, see LICENSE. The underlying services (Ensembl Plants,
Phytozome, TAIR, PlantCyc, BAR) have their own terms of use; check them before
bulk querying.
Available Tools
58 toolsalphafold_structureAlphaFold: Predicted StructureARead-onlyIdempotent
Fetch the AlphaFold DB predicted-structure summary for a locus (alphafold.ebi.ac.uk; free, no key). Resolves the locus → UniProt accession, then returns the predicted model's global mean pLDDT confidence, the per-band pLDDT distribution with each band's pLDDT range (plddt_band_ranges), modelled residue span, latest model version, and mmCIF / PDB / PAE download URLs — links for the client to fetch; no tool on this server retrieves them. A valid protein with no deposited model returns found=false (a normal outcome, not an error); a locus with no UniProt entry raises a typed NotFoundError. Works for all 12 organisms (UniProt-keyed). Complements resolve_locus_to_uniprot (sequence-level) with the structure-level view. Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: locus (required), organism. Returns: AlphaFold DB predicted-structure summary for a locus (via UniProt). The locus i…
analyze_locus_synthSynthesis: Locus OverviewARead-onlyIdempotent
Synthesis: one-call equivalent of the analyze_locus prompt. Resolves a locus through Ensembl Plants, then fans out to xrefs, UniProt, Europe PMC, and QuickGO in parallel. Returns a SynthesisEnvelope with per-step status and a reconciled summary flagging cross-source name/accession disagreements.
Inputs: locus (required), organism. Returns: Composed result of a synthesis orchestrator. ``result`` is ``None`` when the ro…
arabidopsis_natural_variation1001 Genomes: Natural VariationARead-onlyIdempotent
Fetch 1001 Genomes natural-variation SNP effects for an Arabidopsis locus (tools.1001genomes.org; free, no key) — the variation observed across 1135 resequenced natural accessions. Returns per-SNP effect rows (chromosome, position, accession id, effect, impact, amino-acid change, transcript) plus the gene's genomic span. variant_count is the true row total even when capped. ARABIDOPSIS-ONLY — any other organism raises OrganismNotSupported. Defaults to arabidopsis_thaliana.
Inputs: locus (required), cursor, organism. Returns: 1001 Genomes natural-variation SNP effects for an Arabidopsis locus. Arabidopsi…
aragwas_associationsAraGWAS: GWAS AssociationsARead-onlyIdempotent
Fetch AraGWAS genome-wide association study hits for an Arabidopsis locus (aragwas.1001genomes.org; free, no key). Returns each significant SNP association overlapping the gene with its score (-log10 p), minor-allele frequency, the SNP's predicted molecular effect (impact, amino-acid change), and the phenotype/study it came from, including the study's own significance thresholds on the score's scale (study.thresholds), which the over_bonferroni / over_fdr / over_permutation flags are taken against. Rows come strongest first, 25 per answer by default (limit, up to 100); next_cursor resumes at the first row not returned. association_count is the true total even when page-capped. ARABIDOPSIS-ONLY — any other organism raises OrganismNotSupported. Defaults to arabidopsis_thaliana.
Inputs: locus (required), limit, cursor, organism. Returns: AraGWAS GWAS associations for an Arabidopsis locus. Arabidopsis-only. ``associa…
atted_coexpressionATTED-II: CoexpressionARead-onlyIdempotent
Fetch co-expressed gene neighbors from ATTED-II (atted.jp, API v5) for a plant locus. Returns top_n neighbors with target locus + NCBI Entrez gene ID + score (higher = stronger coexpression), in the index the release declares as score_type: 'z' for Ath-u.c4-0, 'LSmr' (logit score) for the other releases. The ATTED-II release (e.g. Ath-u.c4-0 for Arabidopsis, Osa-u.c1-0 for rice) is resolved per-organism. Covers: arabidopsis_thaliana, glycine_max, medicago_truncatula, oryza_sativa, solanum_lycopersicum, vitis_vinifera, zea_mays. Any other organism raises OrganismNotSupported before any request (both the single and batch forms). A locus that is not in the organism's release raises NotFoundError. Pairs with string_interactions to surface high-confidence functional partners (interactors that are also coexpressed).
Inputs: locus (required), top_n, organism. Returns: ATTED-II coexpression response wrapper.
bar_aiv_interactionsBAR: Predicted InteractionsARead-onlyIdempotent
Fetch BAR AIV (Arabidopsis Interactions Viewer) interactions for an Arabidopsis or rice locus. Dispatches by organism: Arabidopsis returns curated GRN paper refs from /interactions/get_paper_by_agi/{locus} (PubMed ID, title, image URL, comments, pipe-split tags; the image is a link for the client to fetch, no tool on this server retrieves it); rice returns predicted PPI partners from /interactions/rice/{locus} with Pearson co-expression r (pcc), evidence hits, and quality score. The kind field discriminates the response shape (grn_papers vs ppi_predictions). Rice requires the MSU LOC_Os* locus format — RAP-DB Osg is rejected upstream. Only Arabidopsis and rice are supported by AIV; other organisms raise OrganismNotSupported.
Inputs: locus (required), organism. Returns: BAR AIV response wrapper — interactions for Arabidopsis or rice. The two BAR AI…
bar_efp_expressionBAR: eFP ExpressionARead-onlyIdempotent
Fetch BAR/eFP world-map natural-variation expression for an Arabidopsis locus. Wraps the world-eFP view at /microarray_gene_expression/world_efp/arabidopsis/{locus} — returns expression across ~36 ecotypes (Bay-0, Col-0, Cvi-1, Ler-2, ...) with per-replicate values, control samples, collection lat/lng, and a per-ecotype mean computed client-side. Arabidopsis only. BAR is keyless and a Global Core Biodata Resource (2023).
Inputs: locus (required). Returns: BAR world-eFP natural-variation expression response wrapper. Wraps ``/microarra…
bar_gene_summaryBAR: Gene SummaryARead-onlyIdempotent
Fetch the BAR (Bio-Analytic Resource, U Toronto) merged ThaleMine + GAIA-aliases summary for an Arabidopsis locus. Returns the TAIR curator summary + Araport11 computational description from /thalemine/gene_information/ together with the NCBI Gene ID and cross-DB aliases (RefSeq, UniProt, TIGR locus-model IDs) from /gaia/aliases/. Arabidopsis only — ThaleMine carries taxon 3702 plus yeast/human for ortholog cross-reference. BAR is keyless and a Global Core Biodata Resource (2023); replaces the v0.9 subscription-gated tair_locus_info stub for the curator-summary use case.
Inputs: locus (required). Returns: BAR ThaleMine + GAIA-aliases response for an Arabidopsis locus. Merges ``/thale…
batch_atted_coexpressionBatch: ATTED-II CoexpressionARead-onlyIdempotent
Batch version of atted_coexpression. Up to 50 loci per call. Covers: arabidopsis_thaliana, glycine_max, medicago_truncatula, oryza_sativa, solanum_lycopersicum, vitis_vinifera, zea_mays. Any other organism raises OrganismNotSupported before any request (both the single and batch forms).
Inputs: loci (required), top_n, organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_bar_aiv_interactionsBatch: BAR Predicted InteractionsARead-onlyIdempotent
Batch variant of bar_aiv_interactions. Fans out per-locus BAR AIV calls in parallel (up to 50 loci); all loci in a single call share the same organism. Each results[locus] is the full single-locus payload (kind=grn_papers for Arabidopsis with papers list, kind=ppi_predictions for rice with partners list).
Inputs: loci (required), organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_bar_gene_summaryBatch: BAR Gene SummaryARead-onlyIdempotent
Batch variant of bar_gene_summary. Fans out per-locus BAR ThaleMine + GAIA-aliases calls in parallel (up to 50 loci). Each results[locus] is the full single-locus payload (curator summary, computational description, NCBI Gene ID, cross-DB aliases). Arabidopsis only.
Inputs: loci (required). Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_ensembl_plants_lookup_locusBatch: Ensembl Plants Locus MetadataARead-onlyIdempotent
Batch variant of ensembl_plants_lookup_locus. Uses Ensembl's native POST /lookup/id endpoint — one HTTP round-trip for up to 50 loci, materially cheaper than N parallel GETs. Successes in results[] with the same shape as the single-locus tool. Retries 429/5xx via the shared _http helper (Retry-After capped at 60 s). Misses (loci with no record) still land in errors[] with the [NotFoundError] prefix; the whole batch only fails when the retry budget is exhausted.
Inputs: loci (required), organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_get_gene_xrefsBatch: Gene Cross-ReferencesARead-onlyIdempotent
Batch variant of get_gene_xrefs. Fans out per-locus xref lookups over Ensembl Plants in parallel (up to 50 loci). Each results[locus] is the full single-locus shape (count + xrefs[] + by_db rollup).
Inputs: loci (required), organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_gramene_homologsBatch: Gramene HomologsARead-onlyIdempotent
Batch version of gramene_homologs. Up to 50 loci per call; shares the homology_type filter across all loci. Returns the standard batch envelope (count + results dict + errors dict).
Inputs: loci (required), homology_type, with_organism, target_organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_kegg_pathwaysBatch: KEGG PathwaysARead-onlyIdempotent
Batch version of kegg_pathways. Up to 50 loci per call. Covers: arabidopsis_thaliana, brachypodium_distachyon, glycine_max, hordeum_vulgare, oryza_sativa, populus_trichocarpa, zea_mays. Any other organism raises OrganismNotSupported before any request (both the single and batch forms).
Inputs: loci (required), organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_locus_callBatch: Any Locus ToolARead-onlyIdempotent
Run one locus-keyed tool over up to 50 loci in one call (#131). 'tool' names any tool whose only required argument is 'locus' (interpro_domains, alphafold_structure, panther_family, orthodb_orthologs, gene_report, ...); 'args' holds that tool's other arguments, shared by every locus and checked against its schema once before any call. Returns the standard batch envelope: results keyed by locus, each exactly what the single tool returns, and per-locus errors. The dedicated batch_* tools remain.
Inputs: loci (required), tool (required), args. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_locus_go_annotationsBatch: GO AnnotationsARead-onlyIdempotent
Batch variant of locus_go_annotations. Two-stage fanout — each locus is resolved to UniProt and then queried in QuickGO. Per-locus NotFoundError from either stage lands in errors[] with the typed prefix preserved. Capped at 50 loci.
Inputs: loci (required), limit, organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_locus_literatureBatch: LiteratureARead-onlyIdempotent
Batch variant of locus_literature. Fans out per-locus Europe PMC searches in parallel (up to 50 loci). Each results[locus] is the full single-locus payload (query + hitCount + returned + hits[]).
Inputs: loci (required), size, organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_phytozome_lookup_locusBatch: Phytozome Locus MetadataARead-onlyIdempotent
Batch variant of phytozome_lookup_locus. Fans out per-locus BioMart queries in parallel (up to 50 loci). Each results[locus] is the full single-locus row (organism_name, gene_name, chromosome, start/end/strand, description).
Inputs: loci (required), organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_resolve_locus_to_uniprotBatch: Resolve Locus → UniProtARead-onlyIdempotent
Batch variant of resolve_locus_to_uniprot. Fans out per-locus UniProtKB searches in parallel (up to 50 loci). Each results[locus] is the full single-locus record (primaryAccession + uniProtkbId + entryType + geneNames + organism + sequenceLength + web_url + …).
Inputs: loci (required), organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
batch_string_interactionsBatch: STRING InteractionsBRead-onlyIdempotent
Batch version of string_interactions. Up to 50 inputs per call. The argument was called loci_or_accessions before #129; that name is still accepted, deprecated.
Inputs: loci (required), limit, organism. Returns: Shared response shape for every ``batch_*`` tool. All batch tools fan out per-l…
biological_context_synthSynthesis: Biological ContextARead-onlyIdempotent
Synthesis: one-call equivalent of the biological_context prompt. Resolves UniProt accession, then fans out to Gramene homologs, KEGG pathways, STRING-DB partners, and ATTED-II coexpression in parallel. Adds a consensus_partners ranking that merges STRING + ATTED scores.
Inputs: locus (required), top_n, organism. Returns: Composed result of a synthesis orchestrator. ``result`` is ``None`` when the ro…
blast_sequenceBLAST: Sequence Search (NCBI)ARead-only
Run a BLAST sequence-similarity search against NCBI BLAST URLAPI. Async Put/Get under the hood — submits the query, polls the RID (honoring NCBI's per-RID 60s floor), and returns the parsed top hits + raw text report excerpt. Programs: blastn / blastp / blastx / tblastn / tblastx. Database defaults to swissprot for protein programs, core_nt for nucleotide. Emits notifications/progress on each poll. Long searches (>10 min) raise [UpstreamUnavailableError] with the RID preserved so the client can re-poll. Set PLANT_GENOMICS_MCP_NCBI_EMAIL to identify the request per NCBI etiquette.
Inputs: sequence (required), expect, program, database, +4 more. Returns: NCBI BLAST URLAPI search result wrapper. Async-submit + poll + fetch is hidden…
consensus_homologsSynthesis: Consensus HomologsARead-onlyIdempotent
Synthesis: cross-source homology consensus. Resolves UniProt + FASTA sequence, then runs Gramene homology calls and NCBI BLAST in parallel. Dedupes hits by normalized locus token and scores by n_sources * mean_identity — Gramene contributes identity=1.0, BLAST contributes pident/100.
Inputs: locus (required), top_n, organism. Returns: Composed result of a synthesis orchestrator. ``result`` is ``None`` when the ro…
ensembl_plants_assemblyEnsembl Plants: AssemblyARead-onlyIdempotent
Describe an organism's Ensembl assembly (rest.ensembl.org /info/assembly; free, no key): assembly name, GCA accession and date, the karyotype, and every top-level seq-region with its length. The names are the region values ensembl_region_query takes, and a start past a region's length is refused there, so a region walk can be planned before the first call. Karyotype regions come first, in karyotype order, then unplaced scaffolds and contigs, longest first. Names are Ensembl's: tomato's chromosomes are CM001064.4 and so on, not '1'. coord_system labels differ between assemblies (chromosome, scaffold, supercontig, primary_assembly), so in_karyotype, not coord_system, says which regions are chromosomes. total counts every region before limit; truncated=true when limit cut some off (soybean has over 1,100).
Inputs: organism (required), limit. Returns: An organism's Ensembl assembly and its top-level seq-regions.
ensembl_plants_lookup_locusEnsembl Plants: Locus MetadataARead-onlyIdempotent
Fetch metadata for a plant locus identifier from Ensembl Plants. Defaults to arabidopsis_thaliana; pass organism= for other plant species (oryza_sativa, zea_mays, ...). Locus is the TAIR-style identifier (e.g. AT1G01010 for Arabidopsis NAC001).
Inputs: locus (required), organism. Returns: Ensembl Plants ``/lookup/id/{locus}`` response. Ensembl returns a documented co…
ensembl_plants_paralogsEnsembl Plants: ParalogsARead-onlyIdempotent
List the paralogues Ensembl Compara (plants) records for a plant locus (rest.ensembl.org /homology, type=paralogues; free, no key). Each row gives the paralogue's locus, its type — within_species_paralog, or other_paralog: Ensembl's 'ancient paralogues', inferred across a super tree, so the two genes can sit in different gene trees — the taxonomy_level of the duplication, perc_id/perc_pos and protein_id, closest first. gramene_homologs carries only within_species_paralog, so a gene can have paralogues here and none there. A paralogue list is not a family list: other_paralog can name a gene outside the family (AT2G23390, an acyl-CoA N-acyltransferase-like gene, is an other_paralog of the ARFs); test membership with interpro_domains. An empty list means Compara records no paralogue, not that the gene is single-copy (FLS2, AT5G46330, has none). found=false when Compara keeps no homology record for the gene at all (e.g. a non-coding gene); an id Ensembl does not know is a not-found error. total and counts_by_type count before limit; truncated=true when limit cut some off.
Inputs: locus (required), limit, organism. Returns: The paralogues Ensembl Compara (plants) records for one locus.
ensembl_region_queryGenomic Region → FeaturesARead-onlyIdempotent
List features overlapping a genomic interval via Ensembl Plants /overlap/region. region is the seq-region name (chromosome / contig, e.g. '1'); start and end are 1-based inclusive. feature is one of gene / transcript / cds / exon (default gene). Answers 'what genes are in this QTL interval / assembly window' without a per-locus lookup. Ensembl caps the span — oversized regions error. ensembl_plants_assembly lists an organism's region names and their lengths; a region outside that list, or a start past its length, is an error here. Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: end (required), start (required), region (required), feature, +1 more. Returns: Ensembl ``/overlap/region/{species}/{region}`` wrapper. Ensembl returns a top-l…
entry_membersFamily / Domain MembersARead-onlyIdempotent
List every protein in one organism that carries an InterPro, Pfam or PANTHER entry, with the gene locus each maps to — the reverse of interpro_domains / panther_family (entry -> genes, not gene -> entries). One UniProt query (rest.uniprot.org; free, no key). Each member gives accession, symbol and locus; locus is the id the locus-keyed tools accept, or null when UniProt links the protein to no gene (e.g. an old cDNA submission). reviewed_only=true (default) keeps Swiss-Prot entries: complete for Arabidopsis and rice, empty for most other crops, so pass reviewed_only=false there. total is UniProt's count across all pages; when truncated=true, pass next_cursor back as cursor= for the next page. An entry absent from the organism is ok with total 0. Defaults to arabidopsis_thaliana.
Inputs: entry (required), cursor, organism, page_size, +1 more. Returns: Every protein in one organism that carries a family/domain entry.
experimental_interactionsThaleMine: Experimental InteractionsARead-onlyIdempotent
Fetch CURATED EXPERIMENTAL protein/genetic interaction partners for an Arabidopsis locus from ThaleMine (BAR's InterMine instance; free, no key), sourced from BioGRID, IntAct and PSI-MI. Unlike string_interactions (predicted / text-mined, scored) and bar_aiv_interactions (which returns GRN paper references for Arabidopsis, not partner pairs), every partner here carries the actual experimental provenance: detection method (two hybrid, pull down, genetic interference, ...), PSI-MI relationship type, physical vs genetic class, source database, and the PubMed IDs that reported it. ThaleMine emits one row per evidence record, so rows are aggregated to one entry per partner with evidence_count as a crude support signal; partners are ordered by that count. found=false means the gene is real but has no curated interaction on record — a normal outcome; an unknown locus raises a typed NotFoundError. Arabidopsis only (ThaleMine carries genes for taxon 3702; other organisms raise OrganismNotSupported).
Inputs: locus (required), organism. Returns: Curated experimental interaction partners for a locus (ThaleMine). Distinct fro…
experimental_structuresPDBe: Experimental StructuresARead-onlyIdempotent
Fetch experimentally-solved (X-ray / cryo-EM / NMR) protein structures for a locus from PDBe (www.ebi.ac.uk/pdbe; free, no key). Resolves the locus → UniProt accession, then returns PDBe's best_structures mapping ranked best-first: per entry the PDB id, chain, experimental method, resolution, coverage, and modelled residue span. Most plant proteins have NO deposited structure — that returns found=false (a normal outcome, not an error); a locus with no UniProt entry raises a typed NotFoundError. structure_count is the true total even when the list is capped. Complements alphafold_structure (the predicted view). Works for all 12 organisms (UniProt-keyed). Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: locus (required), organism. Returns: PDBe experimentally-solved structures for a locus (via UniProt). The locus is r…
find_homologs_synthSynthesis: Homolog SearchARead-onlyIdempotent
Synthesis: one-call equivalent of the find_homologs prompt. Runs BLAST then resolves UniProt-shaped subject accessions via the batch UniProt helper. Returns ranked hits each annotated with their UniProt record (or null if subject_id is not a UniProt accession).
Inputs: sequence (required), top_n, program. Returns: Composed result of a synthesis orchestrator. ``result`` is ``None`` when the ro…
gene_reportSynthesis: Gene Report (Markdown dossier)ARead-onlyIdempotent
Synthesis: one-shot 'tell me about this gene' dossier. Resolves a locus through Ensembl Plants + UniProt, then fans out to cross-references, KEGG pathways, STRING interactors, Europe PMC literature, and QuickGO GO terms. Returns a SynthesisEnvelope whose result.markdown is a rendered Markdown gene dossier (the headline output) alongside a structured result.sections mirror; each backend payload appears once, under sections, while steps[] carries status and per-step timing only. The literature section carries no abstracts (abstracts_included: false) and the GO section no withFrom (with_from_included: false); locus_literature and locus_go_annotations return them. result.gene_names labels the Ensembl and UniProt gene names separately when they differ. Any single backend failure degrades that section to an 'Unavailable' note; the rest of the dossier still renders.
Inputs: locus (required), top_n, organism. Returns: Composed result of a synthesis orchestrator. ``result`` is ``None`` when the ro…
gene_tree_membersGene Tree MembersARead-onlyIdempotent
List the member genes of an Ensembl Compara (plants) gene tree (rest.ensembl.org /genetree; free, no key). Name the tree by locus= (any member gene, with organism=) and Ensembl finds the tree that gene is in now, or by gene_tree_id=; exactly one. A gramene_homologs gene_tree_id comes from an older Compara release and may not exist here, so prefer locus=. Each member gives the locus (the id the locus-keyed tools accept), protein_id, species and taxid, and organism (the canonical slug, or null for a species outside this server's 12). target_organism= keeps one organism's members; omit it for every species. total counts members before limit; truncated=true when limit cut some off. gene_tree_id in the answer is the tree served. An unknown tree id, or a locus in no tree, is a not-found error.
Inputs: limit, locus, organism, gene_tree_id, +1 more. Returns: The member genes of one gene tree, optionally one organism's.
get_gene_xrefsGene Cross-ReferencesARead-onlyIdempotent
Fetch cross-database references (UniProt, NCBI Gene, TAIR, ArrayExpress, …) for a plant locus from Ensembl Plants. Defaults to arabidopsis_thaliana; pass organism= for other Ensembl Plants species. Returns count + raw xref list + a by_db rollup keyed on Ensembl's dbname (e.g. 'Uniprot_gn', 'EntrezGene') for fast lookup of a single foreign identifier.
Inputs: locus (required), organism. Returns: Ensembl ``/xrefs/id/{locus}`` wrapper. The MCP outputSchema must be ``type=obje…
get_sequenceGene / CDS / Protein SequenceARead-onlyIdempotent
Fetch a locus's sequence from Ensembl Plants. seq_type is one of genomic / cds / cdna / protein (default protein — the canonical-transcript product). Closes the lookup → fetch → BLAST loop: feed the returned sequence straight to blast_sequence (protein for blastp, cds/cdna for blastn). Defaults to arabidopsis_thaliana; pass organism= for other plant species.
Inputs: locus (required), organism, seq_type. Returns: Ensembl ``/sequence/id/{locus}`` response — a fetched sequence. The fetch half…
go_enrichmentGO / KEGG Enrichment (gene list)ARead-onlyIdempotent
GO + KEGG over-representation analysis for a gene LIST via g:Profiler g:GOSt (biit.cs.ut.ee/gprofiler; free, no API key). Unlike locus_go_annotations (one locus → its terms), this answers 'what is my gene SET enriched for?' — the dominant question for a differential-expression or co-expression cluster. loci is the query gene list (e.g. AT-codes for Arabidopsis, RAP-DB IDs for rice). sources defaults to GO:BP/GO:MF/GO:CC + KEGG; user_threshold is the g:SCS-corrected significance cutoff (default 0.05). Optional background sets a custom statistical domain (default: all annotated genes). Returns enriched[] (term_id/name/p_value/intersection_size/…, capped at top_n by p-value) plus unmapped[] — query loci g:Profiler could not recognize, surfaced so a locus-namespace mismatch is visible. Defaults to arabidopsis_thaliana; pass organism= for any of the 12 species.
Inputs: loci (required), top_n, sources, organism, +2 more. Returns: g:Profiler g:GOSt over-representation wrapper for a gene list. ``enriched`` is…
gramene_homologsGramene HomologsARead-onlyIdempotent
Fetch orthologs and paralogs for a plant locus from Gramene compara (data.gramene.org v69). Default homology_type='ortholog'; pass 'paralog' for in-species duplicates or 'all' for everything. 'ortholog' includes syntenic_ortholog_* rows; homoeologs (polyploid subgenome copies) come back only under 'all', and excluded_categories counts every category the filter left out. Returns target_locus + homology category (type) + shared gene_tree_id per hit (Gramene's tree id; for the tree's members pass the locus to gene_tree_members). Rows carry no taxon unless with_organism=true (adds 'organism' per row) or target_organism is given, which filters to one organism before the cap and adds 'organism' per row. Paralogs here are within_species_paralog only: Gramene drops Compara's other_paralog ('ancient paralogues'); ensembl_plants_paralogs lists both. Pair with resolve_locus_to_uniprot for protein-level enrichment and with blast_sequence for sequence similarity discovery.
Inputs: locus (required), limit, cursor, homology_type, +2 more. Returns: Gramene compara homology response wrapper.
interpro_domainsInterPro: Protein DomainsARead-onlyIdempotent
Fetch the InterPro domain / family architecture for a locus (www.ebi.ac.uk/interpro; free, no key). Resolves the locus → UniProt accession, then returns the protein's InterPro entries — each with accession, name, type (domain / family / homologous_superfamily / …), source_database (Pfam appears here as source_database='pfam', not a separate tool), the integrated InterPro accession, and residue spans — plus a count_by_type rollup. A protein with no annotated domains returns found=true with an empty list; a locus with no UniProt entry raises a typed NotFoundError. domain_count is the true total even when the row list is page-capped. Works for all 12 organisms (UniProt-keyed). Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: locus (required), organism. Returns: InterPro domain / family architecture for a locus (via UniProt). The locus is r…
jaspar_motifJASPAR: Motif MatrixARead-onlyIdempotent
Fetch one JASPAR binding profile by matrix id, including its raw position-frequency matrix (PFM: per-base count vectors keyed A/C/G/T) plus TF class/family, assay type, source species, UniProt accessions, PubMed refs, IUPAC consensus, and the sequence-logo URL (a link for the client to fetch; no tool on this server retrieves it). The drill-down companion to tf_binding_motifs, which returns the derived consensus but not the matrix. Accepts a versioned id (MA0570.1) or a bare base id (MA0570, which resolves to the newest version). Unknown ids raise a typed NotFoundError.
Inputs: matrix_id (required). Returns: A single JASPAR profile including its raw position-frequency matrix. The drill-…
kegg_pathwaysKEGG PathwaysARead-onlyIdempotent
Fetch KEGG pathway memberships for a plant locus from rest.kegg.jp. Returns a list of pathway IDs + names + KEGG category classes the locus participates in. Pairs with locus_go_annotations for the GO-level functional view. Covers: arabidopsis_thaliana, brachypodium_distachyon, glycine_max, hordeum_vulgare, oryza_sativa, populus_trichocarpa, zea_mays. Any other organism raises OrganismNotSupported before any request (both the single and batch forms). Non-Arabidopsis loci are bridged to the NCBI Entrez Gene ID KEGG indexes (returned as entrez_gene_id). A gene KEGG knows with no pathway memberships is an ok answer with pathways=[]; a gene KEGG has no record of raises NotFoundError. KEGG v118+ is case-sensitive on the locus: pass AGI loci as uppercase.
Inputs: locus (required), organism. Returns: KEGG pathway-membership response wrapper.
locus_gene_rifsGeneRIF Functional StatementsARead-onlyIdempotent
Fetch curated GeneRIF functional statements for an Arabidopsis locus from ThaleMine (free, no key). A GeneRIF is a one-sentence, manually curated statement of what the gene does, each anchored to the PubMed ID of the publication that demonstrated it — dense, directly citable functional context that GO terms (locus_go_annotations) and raw abstracts (locus_literature) do not provide. Well-studied genes have many: HY5 (AT5G11260) has 114. Upstream order is preserved because ThaleMine supplies no meaningful ranking, so truncated means later statements were cut, not that they were less relevant. found=false means the gene exists but has no GeneRIF; an unknown locus raises a typed NotFoundError. Arabidopsis only.
Inputs: locus (required), organism. Returns: Curated GeneRIF functional statements for a locus (ThaleMine). GeneRIFs are one…
locus_go_annotationsGO AnnotationsARead-onlyIdempotent
Fetch Gene Ontology annotations for a plant locus from QuickGO (EBI). Free, no API key. The locus is first resolved to a UniProt accession via the same logic as resolve_locus_to_uniprot, then QuickGO is queried by geneProductId. Returns annotations[] with goId/goName/goAspect/qualifier/evidence + a by_aspect rollup ({molecular_function: [{goId, goName}, ...], biological_process: [...], cellular_component: [...]}) deduped on goId so the high-level term set is one read away; by_aspect_deduped_on names that key in the payload. truncated is true when numberOfHits exceeds returned — raise limit (max 100).
Inputs: locus (required), limit, cursor, organism. Returns: QuickGO annotation search wrapper for a plant locus. The locus is first resolve…
locus_literatureLiterature (Europe PMC)ARead-onlyIdempotent
Search Europe PMC for literature mentioning a plant locus. Free, no API key. Returns up to size results (default 10, capped at 25) with title, authors, journal, year, DOI, PMID, open-access status, citation count, abstract, and the article's web_url (a link for the client to open; no tool on this server retrieves it). For non-Arabidopsis species the species common name is appended to the query to disambiguate locus IDs (rice, maize, ...). Pair with resolve_locus_to_uniprot or ensembl_plants_lookup_locus to ground the locus before fanning out to the literature.
Inputs: locus (required), size, cursor, organism, +1 more. Returns: Europe PMC ``/search`` wrapper for a locus query.
locus_plant_ontologyPlant Ontology (PO/TO) TermsARead-onlyIdempotent
Fetch Plant Ontology (PO) + Trait Ontology (TO) + experimental-condition (PECO) annotations for a plant locus from Planteome (browser.planteome.org, AmiGO2/GOlr; free, no API key). Complements locus_go_annotations: QuickGO serves GO (species-agnostic), Planteome serves the plant-specific ontologies — PO (anatomy + developmental stage), TO (traits). The locus is matched across Planteome's searchable bioentity fields and filtered by the organism's NCBI taxon. Returns annotations[] (term_id / term_name / ontology / aspect / evidence / reference) + a by_ontology rollup ({PO: [{term_id, term_name}, ...], TO: [...], PECO: [...]}) deduped on term_id. Planteome names genes by these locus ids for arabidopsis, rice, wheat and tomato only; other organisms are refused, and a gene Planteome has no record of is not found. Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: locus (required), limit, organism. Returns: Planteome PO/TO annotation wrapper for a plant locus. The locus is matched acro…
locus_variantsKnown VariantsARead-onlyIdempotent
List natural (germline) variants overlapping a locus's genomic span via Ensembl (rest.ensembl.org; free, no key). Resolves the locus → gene coordinates, then returns EVA/dbSNP-sourced SNPs and indels with id, source, consequence class, alleles, and clinical significance. variant_count is the true overlap total; the variant list is capped for payload size with truncated flagged. Opens the variation axis (distinct from get_sequence / ensembl_region_query). Works for all 12 organisms. Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: locus (required), limit, organism. Returns: Natural variants overlapping a locus's genomic span (Ensembl /overlap). The loc…
maize_gene_model_translationMaizeGDB: B73 v4 ↔ v5 Gene-Model TranslationARead-onlyIdempotent
Translate maize B73 gene-model IDs between RefGen_v4 (Zm00001d) and RefGen_v5 (Zm00001eb) with MaizeGDB's published translation table. UniProt and Ensembl Plants know only v5 IDs, so a v4 ID answers nothing there until it is translated. direction v4_to_v5 (default) or v5_to_v4. Each ID comes back mapped (targets: one, or several when the model split or merged), no_counterpart (MaizeGDB lists it with no model in the other assembly: report it as unmappable), or not_in_table (MaizeGDB does not list it, so this source says nothing about it). Gene-model IDs only, no transcript suffix; up to 1000 per call. source gives the table's URL (a link for the client to open; no tool on this server retrieves it), its Last-Modified date and sha256, so an answer can be tied to one release of the table.
Inputs: ids (required), direction. Returns: MaizeGDB's B73 gene-model translation for a batch of IDs.
orthodb_orthologsOrthoDB: OrthologsARead-onlyIdempotent
Resolve a locus to its OrthoDB ortholog group and cross-species member genes (data.orthodb.org; free, no key). Searches at the Viridiplantae level, then returns the group metadata (name, evolutionary rate) and member genes grouped by organism (organism, gene id, description). organism_count is the true cluster total; the member list is capped with truncated flagged. found=false when the locus maps to no ortholog group. Works for all 12 organisms. NOTE: unlike the other locus tools, organism= does NOT scope the search — the group is resolved from the locus id alone at the Viridiplantae level, and organism is only validated and echoed back. Passing a mismatched organism therefore still returns the locus's real group. target_organism= DOES filter: it keeps only that organism's members, before the cap, so a 2,000-member group cannot hide rice or wheat behind 'limit'.
Inputs: locus (required), limit, cursor, organism, +1 more. Returns: OrthoDB ortholog group + cross-species member genes for a locus. ``found=False`…
panther_familyPANTHER: Protein FamilyARead-onlyIdempotent
Fetch the PANTHER protein-family classification for a locus (pantherdb.org; free, no key). Returns the PANTHER family and subfamily (id + name) plus curated GO terms grouped by aspect (molecular_function / biological_process / cellular_component), the PANTHER protein class, and pathways. found=false when PANTHER cannot map the locus; a mapped locus can still have a null family or subfamily, which means PANTHER assigns it none. Complements the sequence-homology tools (gramene_homologs / consensus_homologs) with an evolutionary-family view. Works for all 12 organisms. Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: locus (required), organism. Returns: PANTHER protein-family classification for a locus. ``found=False`` (with null/e…
phytozome_lookup_locusPhytozome: Locus MetadataARead-onlyIdempotent
Fetch a gene record from Phytozome BioMart (phytozome-next.jgi.doe.gov). Defaults to arabidopsis_thaliana; pass organism= for other Phytozome proteomes (slug, scientific/common name, or NCBI taxid — e.g. glycine_max, sorghum_bicolor). Locus is the source-genome gene name (e.g. AT1G01010, Glyma.01G000100). Returns organism_name, gene_name, chromosome, gene_start, gene_end, strand, description.
Inputs: locus (required), organism. Returns: Phytozome BioMart gene row. BioMart's TSV is untyped — numeric fields land as s…
plantcyc_locus_infoPlantCyc: Metabolic PathwaysARead-onlyIdempotent
Fetch metabolic annotation for a locus from PlantCyc / the Plant Metabolic Network (pmn.plantcyc.org; free BioCyc web-services API, no key). Walks gene → enzyme → catalyzed reactions → PlantCyc pathways in the organism's PGDB, returning enzymes[] + reactions[] (id/name) + pathways[] (id/name) — the metabolic-pathway view KEGG and GO don't provide. A non-enzymatic gene (e.g. a transcription factor) returns found=false with empty lists, not an error. reaction_count is the true total even when the lists are capped; pathway_count is too, or null (unknown) when the gene catalyzes more reactions than are walked for pathways. 11 organisms have a PGDB (arabidopsis, rice, maize, soybean, grape, poplar, tomato, barley, sorghum, medicago, brachypodium); wheat is not yet mapped. Defaults to arabidopsis_thaliana (AraCyc, the best-curated); pass organism= for other species.
Inputs: locus (required), organism. Returns: PlantCyc / PMN metabolic annotation for a locus. Walks gene → enzyme → reaction…
resolve_locus_to_uniprotResolve Locus → UniProtARead-onlyIdempotent
Resolve a plant locus to its canonical UniProtKB record. Prefers reviewed (Swiss-Prot) entries; falls back to unreviewed (TrEMBL) when no curated record exists (common for non-Arabidopsis plants). organism accepts a canonical slug, scientific/common name, or NCBI taxid (default arabidopsis_thaliana; e.g. oryza_sativa, zea_mays). A gene symbol answers only when it names one locus; a symbol shared by several loci (ARF1) is InvalidArguments listing them. Returns primaryAccession, uniProtkbId, entryType, recommendedName, geneNames, organism, taxonId, sequenceLength, web_url (a link for the client to open; no tool on this server retrieves it). This is the protein-side entry point — pair with InterPro / AlphaFold / Reactome / structural-bio tools.
Inputs: locus (required), organism. Returns: Normalized UniProtKB record for a single locus. Mirrors the dict shape returned…
string_interactionsSTRING: Interaction NetworkARead-onlyIdempotent
Fetch protein-protein interaction partners from STRING-DB (string-db.org). Accepts either a UniProt accession or a locus identifier. A locus goes to STRING's own resolver, except for wheat, whose STRING proteins carry no locus alias: a wheat locus is resolved via UniProt first. Defaults to arabidopsis_thaliana; pass organism= for other plant species (slug, scientific/common name, or NCBI taxid). Returns first-neighbor partners with the combined STRING score plus per-channel sub-scores (experimental, database, textmining, predicted). The argument was called locus_or_accession before #129; that name is still accepted, deprecated.
Inputs: locus (required), limit, organism. Returns: STRING interaction-partners response wrapper.
tair_locus_infoTAIR-Style Locus SummaryARead-onlyIdempotent
Fetch the TAIR curator-vetted Arabidopsis locus summary. Served via BAR/ThaleMine (U Toronto, Global Core Biodata Resource 2023) since TAIR's free per-locus REST API is gated behind a paid Phoenix Bioinformatics subscription. Returns TAIR curator summary + Araport11 computational description + NCBI Gene ID + cross-DB aliases (RefSeq, UniProt, TIGR locus-model IDs). Arabidopsis only. Alias of bar_gene_summary.
Inputs: locus (required). Returns: BAR ThaleMine + GAIA-aliases response for an Arabidopsis locus. Merges ``/thale…
tf_binding_motifsJASPAR: TF Binding MotifsARead-onlyIdempotent
Fetch curated transcription-factor DNA binding motifs for a locus from JASPAR (jaspar.elixir.no; free, no key) — the cis-regulatory view. Resolves the locus → UniProt accession + gene symbol, searches JASPAR by symbol scoped to the organism's taxid, then CONFIRMS each candidate by matching the accession against the profile's uniprot_ids. Returns per motif the JASPAR matrix id, TF class/family, assay type (SELEX / ChIP-seq / PBM / DAP-seq), an IUPAC consensus derived from the position-frequency matrix (e.g. CACGTG, the G-box/ABRE core), motif length, PubMed refs, and the SVG sequence_logo and JASPAR web_url — links for the client to fetch; no tool on this server retrieves them. IMPORTANT: JASPAR's name search is fuzzy, so name-similarity hits belonging to a DIFFERENT gene are returned separately in name_only_matches and must NOT be attributed to this locus; only motifs is UniProt-confirmed. found=false means the gene has no curated profile (not a TF, or its family is unprofiled for that species) — a normal outcome, not an error. Use jaspar_motif to retrieve the raw matrix for any matrix_id. Coverage is Arabidopsis-heavy (1236 profiles) and thin elsewhere (maize 131, soybean 91, wheat 58, tomato 51, rice 10; Brachypodium and sorghum have none). Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: locus (required), organism. Returns: JASPAR TF binding motifs for a locus (via UniProt). JASPAR is indexed by TF *na…
uniprot_id_mappingUniProt: ID Mapping (batch, every entry)ARead-onlyIdempotent
Map a batch of gene, transcript or protein IDs to EVERY UniProtKB entry UniProt's own ID mapping service returns, one job for the whole batch. Use it when a question asks for all accessions, or for many IDs at once: resolve_locus_to_uniprot returns one entry per locus (its best search hit), so a gene with several entries loses the rest. from_db names the IDs' source as UniProt does: Ensembl_Genomes for plant gene IDs such as maize Zm00001eb, rice Os01g, wheat TraesCS (the default), Ensembl_Genomes_Transcript, Ensembl_Genomes_Protein, or Araport for Arabidopsis AGIs. Each ID comes back mapped (accessions, each with entry_type and reviewed) or unmapped (UniProt lists it as failed: it maps to no entry). Up to 500 IDs per call; duplicates are collapsed. upstream_version is the UniProt release. Maize RefGen_v4 IDs (Zm00001d) are not in UniProt: translate them first with maize_gene_model_translation.
Inputs: ids (required), from_db. Returns: UniProt's ID mapping service for a batch of IDs: every entry per ID.
upstream_releaseUpstream ReleaseARead-onlyIdempotent
Report the release a backend's own release endpoint calls current, for the backends whose answers state none (their tools' upstream_version is always null). It is read by a SEPARATE request at query time, so it is not proof of the release that answered any one call: read it before and after a run, and equal values mean no release changed in between. Never cached. ensembl_plants: the Ensembl Genomes release (e.g. '63'); string: the STRING release ('12.0'); quickgo: the GO annotation load date and the GO ontology date; jaspar: the newest ACTIVE release (several are active at once); kegg: the pathway and genes last-update dates (KEGG has no release number). pdbe, aragwas and europe_pmc publish no data release: release is null and reason says why. Backends whose answers state or pin their release (UniProt, InterPro, PANTHER, AlphaFold, Gramene, ATTED-II, OrthoDB) are not listed: read upstream_version on their answers instead.
Inputs: backend (required). Returns: The release a backend's own endpoint calls current (gap provenance-null-rate).
vep_annotateVEP: Variant EffectARead-onlyIdempotent
Predict a variant's molecular consequences with Ensembl VEP (rest.ensembl.org; free, no key). Variant-first (not locus-first): supply an Ensembl region (chr:start-end:strand, e.g. '1:10000-10000:1') and an alternate allele (e.g. 'C'); returns the most-severe consequence plus one row per overlapping transcript (consequence terms, IMPACT, and SIFT when the variant is coding-missense; the polyphen fields stay null, as Ensembl runs PolyPhen for human only). found=false when Ensembl reports no overlapping feature. Works for all 12 organisms. Defaults to arabidopsis_thaliana; pass organism= for other species.
Inputs: allele (required), region (required), organism. Returns: Ensembl VEP consequence prediction for a variant (region + allele). Variant-fir…
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 58 tools
Most tools target a distinct backend+action, but the synthesis layer (gene_report, analyze_locus_synth, biological_context_synth, find_homologs_synth, consensus_homologs) overlaps heavily with the single-purpose tools they wrap, and bar_gene_summary is explicitly an alias of tair_locus_info. batch_locus_call can also execute almost any locus tool, duplicating every dedicated batch_* tool, leaving real selection ambiguity despite verbose descriptions.
Names are all snake_case and mostly verb_noun (get_sequence, resolve_locus_to_uniprot, kegg_pathways), but the set mixes backend-prefixed names (ensembl_plants_lookup_locus, bar_*, phytozome_*), noun-only physiology names (alphafold_structure, panther_family), batch_* prefixes, and a *_synth suffix convention. Readable, but no single predictable pattern across all 58.
58 tools is far above the well-scoped 3-15 range. The count is inflated by a full batch_* mirror of nearly every single-locus tool plus five synthesis wrappers, and batch_locus_call already generalizes the batch pattern, so many tools do not earn an independent place.
The surface covers the full plant-genomics lifecycle: locus lookup, sequence retrieval, BLAST, UniProt resolution, xrefs, GO/PO/PlantCyc/KEGG annotation, coexpression, STRING/AIV/ThaleMine interactions, structures (AlphaFold/PDBe/InterPro/PANTHER), variants/VEP, GWAS, homology, and literature, with batch and synthesis conveniences. No meaningful dead ends for the stated domain.
Maintenance
Related MCP Connectors
Brassica and canola genes, pangenomes, stress expression, genotypes, germplasm and papers
Pulse and legume genes, LIS gene families, expression, QTL, germplasm and papers
Scientific plotting for bioinformatics with about 160 free modules. Anonymous access supported.
Protein research over UniProtKB: search by function, fetch curated records, map IDs, proteomes.
Related MCP Servers
- AlicenseAqualityAmaintenanceSearches 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.6238 PyPI4MIT
- AlicenseAqualityBmaintenanceGrounds gene-nomenclature work in the HUGO Gene Nomenclature Committee (HGNC) dataset, enabling resolution of gene symbols and IDs to canonical HGNC identifiers, plus cross-references and batch operations.9MIT
- AlicenseNot gradedqualityAmaintenanceRead-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.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server providing public plant bioinformatics APIs including UniProt, NCBI, InterProScan, PDB, AlphaFold, Ensembl Plants, and web-based resources like Sol Genomics and BAR, without local data. It supports gene lookups, protein summaries, structure retrieval, and functional annotations through natural language.MIT