GeneBe MCP

Official

Overview Schema Source Related Servers Discussions Admin

annotate_variant

Read-onlyIdempotent

Classify one human genetic variant from coordinates, HGVS, rsID, SPDI, or gene/protein notation; returns ACMG verdict, population frequency, predictors, ClinVar, and transcript consequences.

Instructions

Annotate and classify one human genetic variant using GeneBe.

Start here for any question about a variant (what is it, is it pathogenic/benign, how common is it). Returns the ACMG verdict with points and criteria, population frequency (gnomAD), predictor scores (REVEL, AlphaMissense, SpliceAI, ...), ClinVar status, transcript consequences, and links to the GeneBe page to cite. Research use only; not a diagnosis.

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": {
      "variant": "<variant>"
    },
    "name": "annotate_variant"
  }
}

Input Schema

Name	Required	Description	Default
`genome`	No	Genome build of coordinate input. Ignored for HGVS/rsID.	hg38
`variant`	Yes	The variant. Accepts 'chr-pos-ref-alt' (6-160585140-T-G), HGVS with transcript (NM_005577.4:c.4195A>C), rsID (rs41272110), SPDI, or 'GENE p.Thr1399Pro'.
`transcript`	No	Force this transcript for the classification, e.g. NM_000546.6
`gene_symbol`	No	Force this gene for the classification, e.g. TP53

Output Schema

Name	Required	Description	Default
`gene`	Yes
`dbsnp`	Yes
`links`	Yes
`scores`	Yes
`clinvar`	Yes
`summary`	No	Human-readable variant summary from GeneBe, when the backend provides one
`variant`	Yes
`verdict`	Yes
`warning`	No
`frequency`	Yes
`truncated`	No
`disclaimer`	No		For research use only. Not a diagnosis; results must be reviewed by a qualified specialist before any clinical use.
`consequences`	Yes
`conservation`	Yes
`total_consequences`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so the safety profile is covered. The description adds genuine value beyond that: the returned evidence categories (ACMG verdict with points/criteria, gnomAD frequency, REVEL/AlphaMissense/SpliceAI scores, ClinVar status, transcript consequences, citation links) plus the 'research use only; not a diagnosis' caveat. Minor gap: it doesn't state whether results are cached or how quickly they change, but the openWorld hint covers external data.

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?

The first sentence is front-loaded with the core action, and the routing hint follows immediately. The return-value enumeration is somewhat long, but since the output schema exists it is arguably redundant rather than wasteful, keeping this just below top marks.

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?

With an output schema present, full annotation coverage, and a low-weight parameter surface, the description supplies everything an agent still needs: routing intent, a research-use disclaimer, and a summary of returned evidence. Nothing essential is missing for a correct call.

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 description coverage is 100% and each parameter carries an example, so baseline is 3. The description adds nothing about input formats beyond what the schema already documents (variant encodings, genome builds, transcript override), so it neither compensates nor detracts.

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 specific verb+resource ('Annotate and classify one human genetic variant using GeneBe'), which unambiguously separates it from siblings like convert_variant or get_gene. An agent can determine the tool's function without inspecting the schema.

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?

The explicit routing statement 'Start here for any question about a variant (what is it, is it pathogenic/benign, how common is it)' gives a clear when-to-use signal. However, no explicit exclusions or named alternatives (e.g., use convert_variant for coordinate transforms, liftover_coordinate for build changes) are provided, so the sibling differentiation is only implied.

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

Deploy Server