AlphaFold Sovereign MCP

Overview Schema Source Related Servers Discussions Admin

Generate Precision Medicine Variant Report

generate_variant_clinical_report

Read-onlyIdempotent

Generate a structured report cross-referencing up to seven biomedical databases for an HGVS variant, separating source classifications from computational evidence without assigning a clinical tier.

Instructions

Generate a multi-source variant interpretation report.

Cross-references evidence from up to seven upstream databases for a single HGVS variant into one structured research report. It preserves source classifications and computational observations separately; it does not assign an independent clinical tier or establish ACMG criteria.

Ensembl VEP — functional consequence, SIFT/PolyPhen/CADD predictions
ClinVar — clinical pathogenicity classifications and review status
gnomAD v4 — population allele frequencies (gnomAD v4, ~807k individuals)
AlphaMissense — deep-learning missense pathogenicity (Cheng et al. 2023)
Open Targets — disease-gene evidence scores
DisGeNET — curated gene-disease association scores
ChEMBL — approved drugs acting on the gene product

The report includes unassessed ACMG-related computational signals, sequence consequences, and gene-level drug context. It does not compute variant-specific three-dimensional structural impact.

Input Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.5.9Oct 30, 2026

changedInput schema / properties / params / properties / hgvs / description

Previous value: -"HGVS expression — gene-relative (preferred): 'BRCA1:c.181T>G'; or RefSeq-based: 'NM_007294.3:c.181T>G'."New value: +"HGVS expression. Gene-relative 'BRCA1:c.181T>G' is candidate discovery only; a versioned transcript such as 'NM_007294.4:c.181T>G' permits exact transcript-text matching, not an independent clinical allele validation."

Changed3 schema fields changedv1.5.2Oct 14, 2026

addedInput schema / properties / params / properties / include_literature_evidence

Added value: +{
+  "default": false,
+  "description": "Opt in to source-attributed PDBe/IUCr text-mined evidence at an explicit UniProt coordinate.",
+  "type": "boolean"
+}

addedInput schema / properties / params / properties / literature_uniprot_id

Added value: +{
+  "anyOf": [
+    {
+      "pattern": "^(?:[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9](?:[A-Z][A-Z0-9]{2}[0-9]){1,2})$",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "UniProt accession of the explicit residue query; not inferred from HGVS."
+}

addedInput schema / properties / params / properties / literature_uniprot_residue

Added value: +{
+  "anyOf": [
+    {
+      "minimum": 1,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "One-based UniProt reference residue; not a PDB or model-local index."
+}

First observedv1.1.8May 29, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), and the description adds real behavioral context beyond them: it preserves source classifications and computational observations separately rather than fusing them, and it explicitly labels ACMG-related signals as 'unassessed' and out of scope for tier assignment. Not disclosed: latency/cost of hitting seven databases, behavior on unresolved or invalid HGVS, or partial-source failure handling.

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?

Front-loaded with the core claim, then scope, then a scannable numbered source list, then two negative boundaries. The seven-item list is long but each entry adds real information about coverage. Minor redundancy between the closing sentences and the earlier 'does not assign an independent clinical tier' statement.

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 read-only aggregation tool with a populated output schema, the description supplies what the structured fields cannot: the exact source coverage, the separation of source classification from computed signal, and the two claims the tool deliberately does not make. Return values needn't be explained given the output schema, and no destructive or permission behavior needs stating for a readOnly tool.

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?

The description never mentions any parameter by name — include_drug_context, include_population_breakdown, include_literature_evidence, and the UniProt accession/residue pair are only discoverable in the schema. The seven-source enumeration does implicitly signal that drug context (ChEMBL) and literature evidence are opt-in surfaces, but no defaults or gating logic are conveyed. Nested property descriptions are detailed, so the schema carries the semantics and a 3 baseline is appropriate.

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 first sentence names a specific verb and artifact ('Generate a multi-source variant interpretation report') and the second scopes it to 'a single HGVS variant' aggregating seven named upstream sources. It also draws explicit negative boundaries against siblings — no independent clinical tier / ACMG criteria (classify_variant_acmg) and no 3D structural impact (triage_variant_3d) — so an agent can separate it from the aggregator-vs-classifier-vs-structural tools without opening schemas.

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?

It clearly establishes the use case: one HGVS variant, research-grade aggregation across seven databases, with exclusions for ACMG tiering and structural computation. What is missing is a positive routing statement naming which tool to use instead when the agent does want a clinical classification or structural triage; the boundaries are conveyed by negation rather than by naming the alternative.

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