plant-genomics-mcp

Overview Schema Source Related Servers Discussions Admin

AlphaFold: Predicted Structure

alphafold_structure

Read-onlyIdempotent

Retrieve AlphaFold structure summaries for plant loci: resolves locus to UniProt, returns pLDDT confidence, model version, and download URLs for mmCIF/PDB/PAE.

Instructions

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.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`locus`	Yes	e.g. AT4G09760 (Arabidopsis), Os01g0100100 (rice RAP-DB)
`organism`	No	Plant organism — accepts canonical slug (arabidopsis_thaliana), scientific or common name, or NCBI taxid	arabidopsis_thaliana

Output Schema

TableJSON Schema

Name	Required	Description
`gene`	No	Gene name from UniProt
`found`	Yes	True if a predicted model exists
`locus`	Yes
`cif_url`	No	mmCIF model download URL — a link for the client to open or fetch; no tool on this server dereferences it
`pdb_url`	No	PDB model download URL — a link for the client to open or fetch; no tool on this server dereferences it
`organism`	No	Organism scientific name
`accession`	Yes	Resolved UniProt accession
`mean_plddt`	No	Global mean pLDDT confidence (0–100)
`description`	No	UniProt protein description
`plddt_bands`	No	Fraction of residues per confidence band
`model_created`	No	Model creation date (ISO 8601)
`pae_image_url`	No	Predicted-aligned-error image URL — a link for the client to open or fetch; no tool on this server dereferences it
`residue_range`	No	Modelled residue span {start, end}
`latest_version`	No	Latest AlphaFold model version
`model_entity_id`	No	e.g. AF-Q9SZ92-F1
`upstream_version`	No	AlphaFold DB release that produced THIS response, as stated by the entry's own latestVersion (e.g. '6'). null means AlphaFold DB did not state one — never that no release exists, and never inferred from a separate metadata call, which can describe a different release than the one that answered.
`plddt_band_ranges`	Yes	Band -> [lower, upper] pLDDT on the 0-100 scale, per EMBL-EBI: very_low <50, low 50-70, confident 70-90, very_high >90

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv1.22.0Sep 24, 2026

changedOutput schema / properties / cif_url / description

Previous value: -"mmCIF model download URL"New value: +"mmCIF model download URL — a link for the client to open or fetch; no tool on this server dereferences it"

changedOutput schema / properties / pae_image_url / description

Previous value: -"Predicted-aligned-error image URL"New value: +"Predicted-aligned-error image URL — a link for the client to open or fetch; no tool on this server dereferences it"

changedOutput schema / properties / pdb_url / description

Previous value: -"PDB model download URL"New value: +"PDB model download URL — a link for the client to open or fetch; no tool on this server dereferences it"

addedOutput schema / properties / plddt_band_ranges

Added value: +{
+  "additionalProperties": {
+    "items": {
+      "type": "integer"
+    },
+    "type": "array"
+  },
+  "description": "Band -> [lower, upper] pLDDT on the 0-100 scale, per EMBL-EBI: very_low <50, low 50-70, confident 70-90, very_high >90",
+  "title": "Plddt Band Ranges",
+  "type": "object"
+}

addedOutput schema / properties / upstream_version

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "AlphaFold DB release that produced THIS response, as stated by the entry's own latestVersion (e.g. '6'). null means AlphaFold DB did not state one — never that no release exists, and never inferred from a separate metadata call, which can describe a different release than the one that answered.",
+  "title": "Upstream Version"
+}

changedOutput schema / required

Previous value: -[
-  "locus",
-  "accession",
-  "found"
-]New value: +[
+  "locus",
+  "accession",
+  "found",
+  "plddt_band_ranges"
+]

Addedv1.18.2Jul 24, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already mark it read-only, idempotent, and non-destructive, but the description adds important behavioral details: it resolves locus to UniProt, returns specific fields (plddt confidence, band ranges, model version, download URLs), and defines edge cases—found=false for valid proteins without a model (a normal outcome) and a typed NotFoundError for missing UniProt entries. This goes well beyond the annotations and gives an agent a clear picture of outcomes.

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

Conciseness5/5

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

The description is dense but well-organized: it opens with the core purpose, enumerates the returned data, covers edge cases and errors, notes the sibling relationship, and closes with defaults. Every sentence contributes value; no filler. It front-loads the primary action and resource, making it easy to scan.

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?

For a tool with two parameters, an output schema, and several nuanced behaviors (resolution, error types, default organism, links-to-fetch-only), the description covers all of them. It even mentions the full organism set (12 organisms, UniProt-keyed). Nothing an agent needs to invoke it correctly is missing.

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

Parameters3/5

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

Schema coverage is 100% and both parameters already have descriptive text (e.g., locus examples, organism acceptors). The description reinforces the default organism and explains the locus resolution, but it does not add significant meaning beyond the schema. Baseline 3 is appropriate given the schema's completeness.

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 opens with a clear verb and resource: 'Fetch the AlphaFold DB predicted-structure summary for a locus', naming the external service and the input type. It also differentiates from the sibling resolve_locus_to_uniprot by explicitly stating this is the structure-level view, so an agent can immediately tell them apart.

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

Usage Guidelines5/5

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

It explicitly names the sibling tool and the distinction ('Complements resolve_locus_to_uniprot (sequence-level) with the structure-level view'). It also gives practical usage context: defaults to arabidopsis_thaliana, the need to pass organism for others, and that the returned URLs are for the client to fetch (not for the tool to download). These are direct when/how-to-use cues.

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

Deploy Server