AlphaFold Sovereign MCP

Overview Schema Source Related Servers Discussions Admin

Query Protein Research Database

query_protein_database

Read-onlyIdempotent

Retrieve proteins already stored in the local knowledge graph and filter them by druggability tier, minimum mean pLDDT, or result limit for local recall without live API calls.

Instructions

Recall proteins already stored in the local knowledge graph.

This is a local-recall query, not a live lookup: it returns only proteins that have previously been written through the knowledge-graph storage API (or retained from earlier versions of the database). No upstream API is called. To assess a protein that may not be stored yet, use assess_target_druggability (druggability tier) or analyze_structural_confidence (pLDDT), which query live sources.

Filters are combined with AND; omit a filter to leave that dimension unconstrained. Returns a JSON record with the applied query, a result_count, and the matching proteins rows. The list is empty when nothing stored matches; an empty result means the local store has no matching row, not that the protein is absent from upstream biology.

Input Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.4.3Jul 30, 2026

changedInput schema / properties / params / properties / druggability_tier / description

Previous value: -"Druggability tier filter."New value: +"Keep only stored proteins with this druggability tier; omit for any tier."

addedInput schema / properties / params / properties / limit / description
```
Added value: +"Maximum rows to return (1–500)."
```

changedInput schema / properties / params / properties / min_plddt / description

Previous value: -"Minimum mean pLDDT confidence score."New value: +"Minimum stored mean AlphaFold pLDDT (0–100; ≥70 = high confidence)."

First observedv1.1.8May 29, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, but the description adds genuinely new behavioral context: no upstream API is called, results are bounded to what was previously written, and empty output has a specific meaning. It does not mention pagination behavior or whether the query costs anything, which keeps it from a 5.

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 definition and the local-vs-live distinction, with no filler sentences. It is slightly verbose, with a parenthetical about earlier database versions and repeated empty-result framing, but every element contributes.

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?

Annotations cover the safety profile and an output schema covers the return shape, so the description's remaining job is disambiguation and empty-result interpretation, both of which it handles thoroughly. For a read-only filtered-list tool, nothing an agent needs to call it correctly is missing.

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?

Context reports 0% schema description coverage (the filters are nested under the required `params` wrapper), so the description must compensate, and it does explain the key non-obvious semantics: filters AND together and an omitted filter leaves that dimension unconstrained. It never names the individual filters (limit, min_plddt, druggability_tier) or their ranges, so an agent still needs the schema for the actual knobs.

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?

States a specific verb and resource ('Recall proteins already stored in the local knowledge graph') and immediately scopes it as local-recall rather than live lookup. It names the specific siblings it is not (assess_target_druggability, analyze_structural_confidence), so it is distinguishable from the 29 other tools without opening a schema.

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?

Gives an explicit when/when-not split: use this for stored proteins, use the two named live-source tools for proteins that may not be stored yet. It also states that an empty result means 'not in local store,' not 'absent from biology,' which prevents a common misuse of the result.

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