AlphaFold Sovereign MCP

Overview Schema Source Related Servers Discussions Admin

Detect Intrinsically Disordered Regions

detect_intrinsically_disordered

Read-onlyIdempotent

Flag contiguous low-pLDDT AlphaFold regions as intrinsic-disorder candidates by grouping residues below 50, returning model-local positions with a caveat that these are not validated disorder.

Instructions

Flag low-confidence modeled regions as intrinsic-disorder candidates.

Reads per-residue AlphaFold pLDDT from PDB C-alpha records and groups contiguous runs below 50. Low pLDDT may reflect intrinsic disorder, missing binding partners, alternate conformations, or model uncertainty; it is NOT independent evidence that a region is disordered.

Returns model-local residue indices, observed PDB chain/residue identifiers, and positional descriptions of low-pLDDT runs. These labels describe model geometry, not validated linkers, tails, disorder or function. Legacy idr_fraction and disordered_residue_count remain deprecated numeric aliases of low-pLDDT measurements, NOT validated intrinsic-disorder assays. Prefer low_plddt_* fields for scientific interpretation. PDB numbering is not mapped to full-length UniProt via SIFTS here.

This implementation is a reproducible screening heuristic, not a validated disorder predictor, biomolecular mechanism classifier, or clinical result. For background on intrinsic disorder, see Ruff & Pappu (2021), J Mol Biol. 433:167208; that paper does not validate these cutoffs or code.

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": "detect_intrinsically_disordered"
  }
}

Input Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.5.2Oct 14, 2026

changedInput schema / properties / params / properties / uniprot_id / description

Previous value: -"UniProt accession, e.g. 'P38398' (BRCA1)."New value: +"UniProt accession (6/10 characters), optionally with isoform suffix (e.g. P04637-2)."

changedInput schema / properties / params / properties / uniprot_id / pattern

Previous value: -"^[A-Z][0-9][A-Z0-9]{3}[0-9](?:[A-Z][0-9][A-Z0-9]{3}[0-9])?$"New value: +"^(?:[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9](?:[A-Z][A-Z0-9]{2}[0-9]){1,2})(?:-[1-9][0-9]*)?$"

First observedv1.1.8May 29, 2026

TDQS

A3.8/5.0

Behavior5/5

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

Annotations already declare read-only, idempotent, closed-world, but the description goes well beyond them: it discloses the 50-pLDDT cutoff, the data source (PDB C-alpha), that PDB numbering is not SIFTS-mapped to full-length UniProt, that legacy fields are deprecated aliases, and repeatedly that outputs are not validated disorder calls. This is exactly the ambiguity-reducing context a caller needs.

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

Conciseness3/5

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

The key caveat is front-loaded well, but the text is long for a one-parameter tool and repeats the same disclaimer three times (labels describe model geometry, legacy fields are not validated assays, this is not a validated predictor). The literature citation at the end is also marginal for tool selection and could be trimmed.

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?

With an output schema present the description need not enumerate return values, and it still characterizes them (residue indices, PDB chain/residue IDs, run positions). Caveats and deprecation notes are thorough; the only gap is the lack of explicit routing against the similar structural-confidence sibling.

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?

There is only one parameter and the property carries its own description of the accession/isoform format, so the schema does most of the work. The description contributes one genuinely useful input-level fact — that residue indices are model-local PDB numbering and are not mapped to full-length UniProt — which affects how the caller must interpret the input/output correspondence.

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 opening sentence gives a specific verb and object (flag low-confidence modeled regions as disorder candidates) and the following sentence explains the exact mechanism: pLDDT from PDB C-alpha records, contiguous runs below 50. It is clear what the tool computes, though it never names a sibling such as analyze_structural_confidence, which plausibly operates on the same pLDDT data, so the differentiation is implicit rather than stated.

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 context is implied ('screening heuristic', 'disorder candidates') and there is explicit guidance on which output fields to trust ('Prefer low_plddt_* fields'), but there is no statement of when to choose this over the clearly related sibling analyze_structural_confidence or get_protein_structure, and no prerequisites beyond the UniProt accession.

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