Skip to main content
Glama

EVEE MCP-Server

MCP-Server für die EVEE (Evo Variant Effect Explorer) API — interpretierbare Vorhersage von Varianten-Effekten basierend auf Evo 2 genomischen Foundation-Model-Embeddings.

EVEE bietet vorab berechnete Pathogenitätsvorhersagen, Disruption-Profile und KI-generierte mechanistische Interpretationen für 4,2 Millionen ClinVar-Varianten. Siehe Pearce et al. (2026) für das vollständige Paper.

Tools

Tool

Beschreibung

search_variants

Suche im Autocomplete-Stil (≤6 Treffer) nach einem Gen-Symbol, rsID oder ClinVar-Variations-ID; nützlich zum Finden von Kandidaten-Varianten-IDs, keine erschöpfende genweite Rangliste

get_variant

Klinische Zusammenfassung, EVEE-abgeleitete Effektausgaben, Datenbank-Vergleichswerte (sofern vorhanden) und die KI-generierte mechanistische Interpretation (löst bei Bedarf automatisch eine Generierung aus, falls noch nicht gespeichert)

wait_for_variant_analysis

Wartet auf die On-Demand-Interpretationsgenerierung von EVEE, bis sie abgeschlossen ist oder ein Timeout auftritt

compare_variants

Zusammenfassung im direkten Vergleich (bis zu 10 Varianten in einem Aufruf) — klinisches Label, Pathogenität, Top-1-Disruption, HGVS, Deep Link

get_variant_disruptions

Die wichtigsten biologischen Annotations-Disruptionen, sortiert nach Ausmaß, optional nach Kategorie gefiltert — erklärt, warum eine Variante als pathogen oder benigne vorhergesagt wird

get_variant_annotations

Vollständige Annotations-Sondenwerte (325 Annotationen in 13 Kategorien), optional nach Kategorie gefiltert

Annotationskategorien

amino_acid, atacseq, ccre, chipseq, chromhmm, elm, fstack, protein_feature, interpro, genomic_feature, ptm, region, secondary_structure

Related MCP server: gnomAD MCP Server

Skill

Ein Claude Code Skill befindet sich unter .claude/skills/evee/SKILL.md. Agenten, die diesen laden, erhalten ca. 120 Zeilen Anleitung zur effektiven Nutzung der Tools — Workflow-Schritte, Zuverlässigkeitshinweise nach Variantenklasse und Fallstricke (0-basierte Koordinaten, Indel-VCF-Verankerung, Groß-/Kleinschreibung).

Verwendung

Erfordert Python 3.10+ und uv.

git clone git@github.com:goodfire-ai/evee-mcp.git
cd evee-mcp
uv sync

Claude Code

Das Repo enthält eine .mcp.json; das Öffnen des Verzeichnisses löst die Berechtigungsabfrage aus:

claude

Claude Desktop

Zur claude_desktop_config.json hinzufügen:

{
  "mcpServers": {
    "evee": {
      "command": "uv",
      "args": ["run", "--directory", "/absolute/path/to/evee-mcp", "python3", "server.py"]
    }
  }
}

Beispiel

Ist die FBN1-Variante rs1597537935 pathogen, und warum?

Der Agent sucht, ruft die klinische Zusammenfassung mit der KI-generierten mechanistischen Interpretation ab und extrahiert die wichtigsten Disruption-Belege.

Available Tools

6 tools
compare_variantsA

Compare multiple variants side-by-side.

Fetches clinical label, pathogenicity score, gene, HGVS protein, consequence, and the top-1 disruption for each. Use when the user asks to contrast, rank, or compare 2+ variants, instead of looping get_variant.

Args: variant_ids: List of variant IDs in chr:pos:ref:alt format (max 10).

Inputs: variant_ids (required).

get_variantA

Get comprehensive information about a specific genetic variant.

Returns clinical significance, model-derived scores from EVEE's heads (aligned to AlphaMissense, CADD, REVEL, SIFT, etc.), reference predictor scores from external databases when present, gene constraint (LOEUF), HGVS notation, disease associations, protein domains, and the AI-generated mechanistic interpretation.

If the stored interpretation isn't ready, this tool hits EVEE's on-demand /analysis endpoint once: if generation has already completed, the fresh interpretation is returned inline; otherwise the response carries an interpretation = {status: queued/processing, detail: ...} entry and you should call wait_for_variant_analysis to poll until it finishes.

Args: variant_id: Variant identifier in chr:pos:ref:alt format (e.g. "chr17:43092918:G:A" for BRCA1 ClinVar ID 41812). NOTE: EVEE uses 0-based positions; ClinVar/VCF/HGVS are 1-based. Subtract 1 from ClinVar pos for SNVs; for indels the offset varies — prefer search_variants.

Inputs: variant_id (required).

get_variant_annotationsA

Get detailed annotation probe values for a variant.

Returns the Evo 2 model's predicted annotation values for both the reference and alternate allele across 325 biological annotations. Each annotation shows ref (reference allele prediction), alt (alternate allele prediction), and delta (alt - ref).

Use this for deep analysis when you need the full picture — e.g., all chromatin marks across tissues, all amino acid probabilities, or every protein feature prediction. For a quick ranked view of what's most disrupted, use get_variant_disruptions instead.

Args: variant_id: Variant identifier in chr:pos:ref:alt format. category: Optional filter. One of: amino_acid, atacseq, ccre, chipseq, chromhmm, elm, fstack, protein_feature, interpro, genomic_feature, ptm, region, secondary_structure. Omit to get ALL annotations.

Inputs: variant_id (required), category.

get_variant_disruptionsA

Get the top biological annotation disruptions for a variant.

Shows which molecular features are most affected by the variant, ranked by magnitude of change. Each disruption shows what the Evo 2 model predicts for the reference vs. alternate allele across 325 biological annotations spanning protein structure, chromatin state, regulatory elements, splice sites, and more.

This is the key tool for understanding WHY a variant is predicted pathogenic or benign — e.g., a splice-site variant might show large disruptions in splice donor/acceptor annotations, while a missense variant might show disruptions in protein domain and secondary structure annotations.

Categories: amino_acid, atacseq, ccre, chipseq, chromhmm, elm, fstack, protein_feature, interpro, genomic_feature, ptm, region, secondary_structure.

Args: variant_id: Variant identifier in chr:pos:ref:alt format. top_n: Number of top disruptions to return (default 15, max 100). category: Optional category filter — restrict ranking to one category (e.g. to see only splice-related disruptions: category='genomic_feature').

Inputs: variant_id (required), top_n, category.

search_variantsA

Autocomplete-style variant lookup (up to 6 matches) in the EVEE database.

The query must be ONE of these exact types — do NOT combine them or add extra words like "pathogenic":

  • A gene name: "BRCA1", "TP53", "FBN1"

  • An rsID: "rs1597537935"

  • A ClinVar variation ID (numeric): "655979"

Returns at most 6 autocomplete-style matches. Pagination/limit params are ignored by the backend.

WARNING: a gene-name query returns an adjacent-position autocomplete slice of variants in that gene — NOT the top-pathogenicity variants of the gene. Do not infer the gene's pathogenic landscape from these 6 rows. To look up a specific variant, query by rsID or ClinVar variation ID.

Use this as the starting point to find variant IDs for the other tools.

Inputs: query (required). Returns: result

wait_for_variant_analysisA

Poll EVEE's on-demand interpretation until it completes or times out.

Use this when get_variant reports interpretation.status as queued or processing. Returns the same curated variant summary as get_variant, plus a wait_status entry with attempts / elapsed_seconds. If the deadline hits before completion, call this tool again to keep polling.

Args: variant_id: Variant identifier in chr:pos:ref:alt format. timeout_seconds: Maximum wall-clock time to wait (clamped to [1, 60]). poll_interval_seconds: Delay between polls (clamped to [0.5, 10]).

Inputs: variant_id (required), timeout_seconds, poll_interval_seconds.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.5/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: search_variants for lookup, get_variant for comprehensive info, compare_variants for side-by-side comparison, get_variant_annotations for deep probes, get_variant_disruptions for top disruptions, and wait_for_variant_analysis for polling. No overlapping functionality.

    Naming Consistency5/5

    All tool names follow the verb_noun pattern in snake_case consistently (e.g., compare_variants, get_variant_annotations). The naming is predictable and easy to understand.

    Tool Count5/5

    With 6 tools, the server covers the core workflows of variant lookup, detailed retrieval, comparison, annotation analysis, disruption ranking, and async waiting. This is well-scoped for a specialized domain without being too few or too many.

    Completeness4/5

    The tool set covers essential operations: search, retrieve, compare, deep annotations, disruptions, and async polling. A minor gap is the lack of a tool to list all variants for a given gene (search_variants only returns up to 6 autocomplete results), but for targeted variant analysis, the surface is sufficiently complete.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI-powered genomic variant analysis including variant impact prediction, regulatory element discovery, and batch variant scoring. Currently operates in mock mode as a proof-of-concept awaiting the public release of Google DeepMind's AlphaGenome API.
      24
      40 npm
      2
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Provides a programmatic interface to the Genome Aggregation Database (gnomAD) API across versions v2.1.1, v3.1.2, and v4.1.0. It enables users to query gene metadata, variant information, population frequencies, and ClinVar data through a unified schema.
      12
      7
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Look up variant allele frequencies by ancestry, gene loss-of-function constraint, gene variant lists, and sequencing coverage over gnomAD — with ClinVar significance joined in — via MCP.
      253 npm
      1
      Apache 2.0