EVEE MCP Server
EVEE MCP Server
MCP-сервер для API EVEE (Evo Variant Effect Explorer) — интерпретируемое прогнозирование эффектов вариантов на основе эмбеддингов геномной фундаментальной модели Evo 2.
EVEE предоставляет предварительно вычисленные прогнозы патогенности, профили нарушений и ИИ-сгенерированные механистические интерпретации для 4,2 миллионов вариантов ClinVar. Полную статью см. в Pearce et al. (2026).
Инструменты
Инструмент | Описание |
| Поиск в стиле автодополнения (≤6 совпадений) по символу гена, rsID или ID вариации ClinVar; полезно для поиска ID вариантов-кандидатов, а не для исчерпывающего ранжирования по всему гену |
| Клиническое резюме, выходные данные эффектов от EVEE, оценки сравнения с базами данных (при наличии) и ИИ-сгенерированная механистическая интерпретация (автоматически запускает генерацию по запросу, если она еще не сохранена) |
| Опрос генерации интерпретации по запросу в EVEE до завершения или истечения времени ожидания |
| Сводка для сравнения (до 10 вариантов за один вызов) — клиническая метка, патогенность, основное нарушение (top-1), HGVS, прямая ссылка |
| Основные нарушения биологических аннотаций, ранжированные по величине, с возможностью фильтрации по категории — объясняет, почему вариант прогнозируется как патогенный или доброкачественный |
| Полные значения проб аннотаций (325 аннотаций по 13 категориям), с возможностью фильтрации по категории |
Категории аннотаций
amino_acid, atacseq, ccre, chipseq, chromhmm, elm, fstack, protein_feature, interpro, genomic_feature, ptm, region, secondary_structure
Related MCP server: gnomAD MCP Server
Навык
Навык Claude Code находится в .claude/skills/evee/SKILL.md. Агенты, загружающие его, получают около 120 строк руководства по эффективному использованию инструментов — этапы рабочего процесса, предостережения о надежности по классам вариантов и нюансы (координаты с 0, привязка VCF для инделей, чувствительность к регистру).
Использование
Требуется Python 3.10+ и uv.
git clone git@github.com:goodfire-ai/evee-mcp.git
cd evee-mcp
uv syncClaude Code
В репозитории есть .mcp.json; открытие директории вызывает запрос на разрешение:
claudeClaude Desktop
Добавьте в claude_desktop_config.json:
{
"mcpServers": {
"evee": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/evee-mcp", "python3", "server.py"]
}
}
}Пример
Является ли вариант FBN1 rs1597537935 патогенным и почему?
Агент выполняет поиск, получает клиническое резюме с ИИ-сгенерированной механистической интерпретацией и извлекает основные доказательства нарушений.
Available Tools
6 toolscompare_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
Scored across 6 tools
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.
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.
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.
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
Related MCP Connectors
Annotate and classify human genetic variants with GeneBe (ACMG, gnomAD, ClinVar). Research use only.
Ancestry allele frequencies, LoF constraint, variant lists, and coverage from gnomAD, with ClinVar.
MyVariant.info MCP. Aggregated human genetic-variant annotation: dbSNP, ClinVar clinical…
Germline ACMG/AMP classification, genes, disease associations, literature and API-key case analysis.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables 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.2413 npm2MIT
- AlicenseBqualityDmaintenanceProvides 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.127Apache 2.0
- AlicenseAqualityDmaintenanceEnables variant annotation and effect prediction using the Ensembl VEP API, with support for batch and single queries.91MIT
- AlicenseNot gradedqualityBmaintenanceLook 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 npm1Apache 2.0