AlphaGenome MCP Server

batch_modality_screen

Rank multiple genetic variants by predicted impact on a chosen modality (expression, splicing, TF binding, chromatin) for batch screening and research prioritization.

Instructions

Rank several variants by predicted effect within one modality: expression (RNA_SEQ, CAGE), splicing (SPLICE_SITES, SPLICE_SITE_USAGE), tf_binding (CHIP_TF) or chromatin (DNASE, ATAC).

Runs live inference (score_variant with the SDK's recommended variant scorers); works for single-nucleotide variants, indels and multi-nucleotide variants. The result states source: live.

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.

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": {
      "variants": "<variants>",
      "modality": "<modality>"
    },
    "name": "batch_modality_screen"
  }
}

Input Schema

Name	Required	Description	Default
`modality`	Yes
`variants`	Yes	Variants to score (1-100)

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv0.3.0Sep 28, 2026
- removedInput schema / properties / modality / description
```
Removed value: -"Regulatory modality to screen"
```
- addedInput schema / properties / variants / description
```
Added value: +"Variants to score (1-100)"
```
- addedInput schema / properties / variants / items / properties / alt / description
```
Added value: +"Alternate allele (A, C, G, T; more than one base for an indel)"
```
- addedInput schema / properties / variants / items / properties / alt / pattern
```
Added value: +"^[ATGCatgc]+$"
```
- addedInput schema / properties / variants / items / properties / chromosome / description
```
Added value: +"Chromosome (chr1-chr22, chrX, chrY)"
```
- addedInput schema / properties / variants / items / properties / chromosome / pattern
```
Added value: +"^chr([1-9]|1[0-9]|2[0-2]|X|Y)$"
```
- addedInput schema / properties / variants / items / properties / position / description
```
Added value: +"Genomic position (1-based, hg38)"
```
- addedInput schema / properties / variants / items / properties / position / minimum
```
Added value: +1
```
- addedInput schema / properties / variants / items / properties / ref / description
```
Added value: +"Reference allele (A, C, G, T; more than one base for an indel)"
```
- addedInput schema / properties / variants / items / properties / ref / pattern
```
Added value: +"^[ATGCatgc]+$"
```
- addedInput schema / properties / variants / items / properties / variant_id
```
Added value: +{
+  "description": "Optional: variant identifier (e.g., rs number)",
+  "type": "string"
+}
```
- addedInput schema / properties / variants / maxItems
```
Added value: +100
```
First observedDec 29, 2025

TDQS

A3.5/5.0

Behavior4/5

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

With no annotations, the description carries the burden well: it discloses live inference execution, supported variant classes (SNV, indel, MNV), the output marker (source: live), and an explicit research-only / non-clinical limitation. It omits operational traits like latency, cost, or whether anything is persisted, which keeps it short of 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?

Three short paragraphs, front-loaded with the core action and modality/scorer mapping, then execution detail, then the caveat. Every sentence contributes; only mild redundancy in the closing 'as returned' phrasing.

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

Completeness3/5

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

For a two-parameter tool with no annotations and no output schema, the description covers what it computes and flags output provenance, but leaves the selection problem unsolved — an agent facing ~20 sibling scoring tools has no basis to choose this one. The core semantics are adequate; the comparative context 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?

Schema coverage is only 50%, and the description compensates by mapping each modality enum value to concrete scorers (RNA_SEQ/CAGE, SPLICE_SITES, CHIP_TF, DNASE/ATAC) — meaning the schema does not carry. It also frames which variant types the variants array accepts, though it adds nothing about the positional/allele constraints already in the schema.

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 (rank) applied to a resource (variants) with an explicit scope (within one modality), and the modality-level framing plus scorer mapping is distinctive. However, it never names or distinguishes itself from near-identical siblings such as batch_score_variants, predict_variant_effect, or compare_variants, so the agent cannot tell from the description alone which to pick.

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

Usage Guidelines2/5

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

No when-to-use, when-not-to-use, or alternative routing is given despite a very crowded sibling set of scoring/prediction tools. The only routing-like sentence ('score_variant with the SDK's recommended variant scorers') describes internal implementation rather than guiding tool selection.

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