Skip to main content
Glama
taehojo

AlphaGenome MCP Server

by taehojo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

predict_variant_effect

Predict the regulatory impact of a genetic variant on gene expression, splicing, chromatin, and transcription factor binding using AlphaGenome model predictions.

Instructions

Predicted regulatory effect of a genetic variant, per modality: the strongest tracks of each scorer (expression, transcription start, chromatin accessibility, histone marks, transcription factor binding, splicing), each with its score, calibrated quantile, gene, tissue or cell type, and assay. From the Atlas the AlphaGenome Variant Impact (AVI) score is included.

Source: a single-nucleotide variant is answered from the precomputed AlphaGenome Atlas; an indel or multi-nucleotide variant runs live inference (score_variant). Both return the same scorers in the same shape. Chosen automatically, overridable with source, and always stated in the result.

The response is a summary, never a full score matrix: ranked rows only, capped at top_n (default 25, max 100) and at 40,000 characters.

Results are AlphaGenome model predictions for research prioritization, not clinical classifications: scores and calibrated quantiles are reported as returned, and no pathogenic/benign call is made.

Example: "Analyze chr19:44908684 T>C with AlphaGenome"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
altYesAlternate allele (A, C, G, T; more than one base for an indel)
refYesReference allele (A, C, G, T; more than one base for an indel)
sourceNoOptional: where the answer comes from (default: auto). auto = the precomputed AlphaGenome Atlas for single-nucleotide substitutions, live inference for everything else (indels, multi-nucleotide variants); falls back to live only when the Atlas does not hold the variant. atlas = Atlas only, errors instead of falling back. live = always run the model. The result always states which source answered.
scorersNoOptional: scorer names to use instead of the defaults. Names come from atlas_list_scorers and are the same for both sources, except the AVI scorers, which the Atlas alone serves.
positionYesGenomic position (1-based, hg38)
chromosomeYesChromosome (chr1-chr22, chrX, chrY)
tissue_typeNoOptional: keep only the tracks of one tissue or cell type. A name (brain, neuron, blood, liver, heart, lung, kidney) or an ontology CURIE (e.g., UBERON:0000955, CL:0000540). Default: all tissues.
output_typesNoOptional: modalities to report (default: one scorer per modality)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.3.0
    • changedInput schema / properties / alt / description
      Previous value: -"Alternate allele (A, T, G, or C)"New value: +"Alternate allele (A, C, G, T; more than one base for an indel)"
    • changedInput schema / properties / output_types / description
      Previous value: -"Optional: specific analyses to run (default: all)"New value: +"Optional: modalities to report (default: one scorer per modality)"
    • changedInput schema / properties / position / description
      Previous value: -"Genomic position (1-based, positive integer)"New value: +"Genomic position (1-based, hg38)"
    • changedInput schema / properties / ref / description
      Previous value: -"Reference allele (A, T, G, or C)"New value: +"Reference allele (A, C, G, T; more than one base for an indel)"
    • addedInput schema / properties / scorers
      Added value: +{
+  "description": "Optional: scorer names to use instead of the defaults. Names come from atlas_list_scorers and are the same for both sources, except the AVI scorers, which the Atlas alone serves.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / source
      Added value: +{
+  "description": "Optional: where the answer comes from (default: auto). auto = the precomputed AlphaGenome Atlas for single-nucleotide substitutions, live inference for everything else (indels, multi-nucleotide variants); falls back to live only when the Atlas does not hold the variant. atlas = Atlas only, errors instead of falling back. live = always run the model. The result always states which source answered.",
+  "enum": [
+    "auto",
+    "atlas",
+    "live"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / tissue_type / description
      Previous value: -"Optional: tissue context (UBERON term, e.g., \"UBERON:0001157\" for brain)"New value: +"Optional: keep only the tracks of one tissue or cell type. A name (brain, neuron, blood, liver, heart, lung, kidney) or an ontology CURIE (e.g., UBERON:0000955, CL:0000540). Default: all tissues."
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and delivers: it discloses auto/live/atlas source selection and fallback, that the result states which source answered, that output is a capped summary rather than a full matrix, and that results are model predictions not clinical calls. A minor issue is that it describes a `top_n` cap (default 25, max 100) that does not appear in the input schema, which could mislead.

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 purpose and then organized into scope, source behavior, response shape, and a caveat, which is efficient paragraphing. It runs a little long and includes the unreconciled `top_n` detail, but every section largely earns its place.

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?

For an 8-parameter, no-annotation, no-output-schema tool, the description covers the response shape (ranked rows, per-modality strongest tracks, character cap), source dispatch, and the research-only caveat. What is missing is explicit sibling differentiation and reconciliation of the `top_n` cap with the actual schema.

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%, so the baseline is 3. The description reinforces source semantics and notes that scorer names come from atlas_list_scorers and that AVI scorers are Atlas-only, but most parameter meaning is already carried by the rich schema, and the phantom `top_n` is never reconciled.

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?

States a specific verb (predicted regulatory effect) and resource (genetic variant) and enumerates the modalities returned (expression, TSS, chromatin, histone, TF binding, splicing) plus the AVI score. It is clear what the tool produces, but it never explicitly contrasts itself with narrower siblings like predict_splice_impact or predict_tissue_specific, so an agent must infer the boundary.

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?

The description explains the automatic source selection and the override via `source`, plus fallback behavior, which is useful invocation guidance, and it gives a concrete example query. However, it offers no when-to-use/when-not guidance relative to the ~20 sibling prediction tools, leaving alternative selection to inference.

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

Deploy Server

Other Tools