AlphaFold Sovereign MCP

Overview Schema Source Related Servers Discussions Admin

Query Variant Research Database

query_variant_database

Read-onlyIdempotent

Search locally stored genetic variants by gene, clinical tier, AlphaMissense score, ClinVar class, or gnomAD frequency to retrieve filtered knowledge-graph records without upstream API calls.

Instructions

Search the local knowledge graph for stored variants.

Returns variants matching the filter criteria. No upstream API calls are made — all data is served from the local SQLite knowledge graph, which is populated only through explicit writes to the knowledge-graph storage API. Historical SQLite files may retain illustrative rows from older versions; these should not be interpreted as independently verified biology.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "params": "<params>"
    },
    "name": "query_variant_database"
  }
}

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 changedv1.4.3Jul 30, 2026
- addedInput schema / properties / params / properties / limit / description
```
Added value: +"Maximum rows to return (1–500)."
```
First observedv1.1.8May 29, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, so the bar is lower, but the description adds real value beyond them: no upstream API calls, data served from local SQLite, population only via the knowledge-graph write API, and an explicit caveat that legacy rows may be illustrative rather than verified biology. That provenance warning is exactly the kind of context annotations cannot carry.

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?

Four short sentences, front-loaded with the action, then reading behavior, then the provenance caveat an agent most needs before trusting results. Nothing is repeated from the schema or annotations.

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

Completeness4/5

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

An output schema exists so return shape need not be explained, and the read-only annotations carry the safety profile. The description covers the source-of-truth question well; the only omission is anything about result ordering, empty-result meaning, or how the nested filters interact.

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

Parameters2/5

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

The top-level 'params' wrapper has no schema description (reported coverage 0% at that level), and the description says nothing about any filter — gene, tier, min_am_score, max_gnomad_af, clinvar_class, limit — nor how filters combine. It does not compensate for the coverage gap; an agent must read the nested properties to learn anything. Nested property descriptions exist, which prevents a score of 1.

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

Purpose4/5

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

The first sentence states a specific verb and resource ('Search the local knowledge graph for stored variants') and the second restates the return behavior. This clearly separates it from compute-oriented siblings like triage_variant_3d or classify_variant_acmg, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

Usage is only implied: the note that data is local and populated only through explicit writes tells an agent that a miss means nothing was stored rather than that the query was wrong. There is no explicit when-to-use versus when-to-use-an-alternative guidance, and no exclusion of other variant tools.

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