Skip to main content
Glama
musharna

plant-genomics-mcp

by musharna

PlantCyc: Metabolic Pathways

plantcyc_locus_info
Read-onlyIdempotent

Fetch metabolic-pathway annotations for a plant locus from PlantCyc, mapping genes to enzymes, reactions, and pathways across 11 plant PGDBs.

Instructions

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 / pathway_count report true totals even when the lists are capped. 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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
locusYese.g. AT3G51240 (Arabidopsis), Os11g0530600 (rice RAP-DB)
organismNoPlant organism — accepts canonical slug (arabidopsis_thaliana), scientific or common name, or NCBI taxidarabidopsis_thaliana

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
foundYesTrue if the locus resolved to a metabolic gene
locusYes
orgidYesPlantCyc PGDB org id, e.g. ARA (AraCyc)
enzymesYesProduct monomer (enzyme) frame ids
organismYesCanonical organism slug
pathwaysYes
reactionsYes
gene_frameNoResolved PGDB gene frame id
pathway_countYesTotal distinct pathways (pre-cap)
reaction_countYesTotal distinct reactions (pre-cap)
gene_common_nameNoGene common name in the PGDB

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed21 schema fields changedv1.18.2
    • changedInput schema / properties / locus / description
      Previous value: -"TAIR-canonical locus, e.g. AT1G01010"New value: +"e.g. AT3G51240 (Arabidopsis), Os11g0530600 (rice RAP-DB)"
    • addedInput schema / properties / organism
      Added value: +{
      +  "default": "arabidopsis_thaliana",
      +  "description": "Plant organism — accepts canonical slug (arabidopsis_thaliana), scientific or common name, or NCBI taxid",
      +  "type": [
      +    "string",
      +    "integer"
      +  ]
      +}
    • addedOutput schema / $defs
      Added value: +{
      +  "PlantCycPathway": {
      +    "additionalProperties": true,
      +    "description": "One PlantCyc/PMN pathway the locus participates in.",
      +    "properties": {
      +      "id": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "default": null,
      +        "description": "Pathway frame id, e.g. PWY-6787",
      +        "title": "Id"
      +      },
      +      "name": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "default": null,
      +        "description": "Pathway common name, e.g. flavonoid biosynthesis",
      +        "title": "Name"
      +      }
      +    },
      +    "title": "PlantCycPathway",
      +    "type": "object"
      +  },
      +  "PlantCycReaction": {
      +    "additionalProperties": true,
      +    "description": "One reaction catalyzed by a locus's gene product (PlantCyc/PMN).",
      +    "properties": {
      +      "id": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "default": null,
      +        "description": "Reaction frame id, e.g. RXN-7775",
      +        "title": "Id"
      +      },
      +      "name": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "default": null,
      +        "description": "Reaction common name, if the frame has one",
      +        "title": "Name"
      +      }
      +    },
      +    "title": "PlantCycReaction",
      +    "type": "object"
      +  }
      +}
    • changedOutput schema / description
      Previous value: -"PlantCyc stub response — adds ``plantcyc_web_url`` to the shared shape."New value: +"PlantCyc / PMN metabolic annotation for a locus.\n\nWalks gene → enzyme → reactions → pathways in the organism's PGDB via the\nfree BioCyc web-services API. ``found=False`` with empty lists when the\nlocus has no metabolic annotation (e.g. a non-enzymatic gene like a\ntranscription factor) — this is a normal result, not an error.\n``reaction_count`` / ``pathway_count`` are the true totals even when the\nreturned lists are capped (see ``plantcyc.MAX_REACTIONS`` / ``MAX_PATHWAYS``)."
    • removedOutput schema / properties / alternatives
      Removed value: -{
      -  "description": "Tool names users should call instead",
      -  "items": {
      -    "type": "string"
      -  },
      -  "title": "Alternatives",
      -  "type": "array"
      -}
    • removedOutput schema / properties / alternatives_note
      Removed value: -{
      -  "description": "What the alternatives do and do NOT cover",
      -  "title": "Alternatives Note",
      -  "type": "string"
      -}
    • addedOutput schema / properties / enzymes
      Added value: +{
      +  "description": "Product monomer (enzyme) frame ids",
      +  "items": {
      +    "type": "string"
      +  },
      +  "title": "Enzymes",
      +  "type": "array"
      +}
    • addedOutput schema / properties / found
      Added value: +{
      +  "description": "True if the locus resolved to a metabolic gene",
      +  "title": "Found",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / gene_common_name
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Gene common name in the PGDB",
      +  "title": "Gene Common Name"
      +}
    • addedOutput schema / properties / gene_frame
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Resolved PGDB gene frame id",
      +  "title": "Gene Frame"
      +}
    • addedOutput schema / properties / organism
      Added value: +{
      +  "description": "Canonical organism slug",
      +  "title": "Organism",
      +  "type": "string"
      +}
    • addedOutput schema / properties / orgid
      Added value: +{
      +  "description": "PlantCyc PGDB org id, e.g. ARA (AraCyc)",
      +  "title": "Orgid",
      +  "type": "string"
      +}
    • addedOutput schema / properties / pathway_count
      Added value: +{
      +  "description": "Total distinct pathways (pre-cap)",
      +  "title": "Pathway Count",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / pathways
      Added value: +{
      +  "items": {
      +    "$ref": "#/$defs/PlantCycPathway"
      +  },
      +  "title": "Pathways",
      +  "type": "array"
      +}
    • removedOutput schema / properties / plantcyc_web_url
      Removed value: -{
      -  "description": "Browser URL for the PlantCyc gene page",
      -  "title": "Plantcyc Web Url",
      -  "type": "string"
      -}
    • removedOutput schema / properties / probed_at
      Removed value: -{
      -  "description": "ISO date of the last live access probe (YYYY-MM-DD)",
      -  "title": "Probed At",
      -  "type": "string"
      -}
    • removedOutput schema / properties / rationale
      Removed value: -{
      -  "description": "Why this backend is gated",
      -  "title": "Rationale",
      -  "type": "string"
      -}
    • addedOutput schema / properties / reaction_count
      Added value: +{
      +  "description": "Total distinct reactions (pre-cap)",
      +  "title": "Reaction Count",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / reactions
      Added value: +{
      +  "items": {
      +    "$ref": "#/$defs/PlantCycReaction"
      +  },
      +  "title": "Reactions",
      +  "type": "array"
      +}
    • removedOutput schema / properties / status
      Removed value: -{
      -  "description": "Always \"subscription_required\" — upstream REST is paid-only.",
      -  "title": "Status",
      -  "type": "string"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "locus",
      -  "status",
      -  "probed_at",
      -  "rationale",
      -  "alternatives",
      -  "alternatives_note",
      -  "plantcyc_web_url"
      -]New value: +[
      +  "locus",
      +  "organism",
      +  "orgid",
      +  "found",
      +  "enzymes",
      +  "reactions",
      +  "pathways",
      +  "reaction_count",
      +  "pathway_count"
      +]
  2. First observedv1.8.0

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnlyHint, idempotentHint, etc.), the description adds that the tool walks gene→enzyme→catalyzed reactions→pathways, returns found=false for non-enzymatic genes without error, caps lists but reports true totals via reaction_count/pathway_count, and details response structure (enzymes[], reactions[], pathways[]). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with front-loaded purpose, followed by walkthrough, special cases, count behavior, and supported organisms. Every sentence adds value, though it is somewhat lengthy. No redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of annotations and an output schema, the description provides all necessary information: purpose, input parameters with extra context, behavioral details (non-enzymatic handling, capped lists, true totals), supported organisms, and contrast with other resources. It is complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds significant meaning: for 'organism', it specifies accepted formats (slug, scientific/common name, NCBI taxid) and lists the 11 supported organisms; for 'locus', it provides examples (AT3G51240, Os11g0530600). Default organism is stated. This goes beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches metabolic annotations for a locus from PlantCyc, specifying the walkthrough from gene to enzyme to reactions to pathways. It explicitly distinguishes itself from KEGG and GO, and lists supported organisms and the default. The verb 'fetch' with the resource 'metabolic annotation for a locus' is specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates when to use (to get metabolic-pathway view not provided by KEGG/GO) and which organisms are supported (listing 11, noting wheat is not mapped). It also explains behavior for non-enzymatic genes. However, it does not explicitly mention when not to use or directly contrast with siblings like kegg_pathways, though the differentiation is implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.