opentargets-mcp

概述

此 MCP 服务器通过其全面的工具集将 Open Targets Platform 的 GraphQL API 暴露给 AI 客户端。它涵盖靶点分析、疾病研究、药物发现、证据挖掘、变异分析和研究探索。该实现专注于实际生物医学工作流程，具有严格的 ID 解析、类型化参数处理和高效的数据过滤功能。

试试问 AI

装完之后，这里有 5 个你可以让 AI 做的事：

• get_target_info

  Core target identity record (Ensembl IDs, synonyms, genomic coordinates)

  试试:Get information about the EGFR target试试:Show me details for the TP53 gene
• get_disease_info

  Disease/EFO summary with therapeutic area context

  试试:Get information about schizophrenia试试:Show me details for type 2 diabetes
• get_drug_info

  ChEMBL-backed drug profile and mechanism data

  试试:Get information about osimertinib试试:Show me details for aspirin
• search_entities

  Unified entity search with synonym handling

  试试:Search for targets related to Alzheimer's试试:Find drugs for breast cancer
• get_target_associated_diseases

  High-confidence target-disease links with scores

  试试:What diseases is BRCA1 associated with?试试:Show diseases linked to EGFR
• get_target_disease_evidence

  Evidence details across genetics, expression, and literature

  试试:Get evidence for TP53 and lung cancer试试:Show evidence linking EGFR and glioblastoma
• get_drug_repurposing_candidates

  Multi-hop disease -> target -> drug candidate prioritization

  试试:Find repurposing candidates for inflammatory bowel disease试试:What drugs could be repurposed for Alzheimer's?
• get_variant_info

  Information about genetic variants

  试试:Get details about the rs12345 variant试试:Show information about rs6764265
• get_study_info

  Information about GWAS studies

  试试:Get details about study ABC123试试:Show information for GWAS study UK Biobank 1234
• graphql_query

  Execute a raw GraphQL query

  试试:Run a GraphQL query for target expression data试试:Get all known drug-target interactions via GraphQL
• map_ids

  Map between different identifier systems

  试试:Convert EGFR to Ensembl ID试试:Map ChEMBL123 to drug name
• get_drug_adverse_events

  Adverse event information for a drug

  试试:What adverse events are associated with osimertinib?试试:Show adverse events for metformin

可对比工具

安装

pip install mcpm
mcpm install opentargets

uvx --from git+https://github.com/nickzren/opentargets-mcp opentargets-mcp

git clone https://github.com/nickzren/opentargets-mcp
cd opentargets-mcp
pip install uv
uv sync
uv run python -m opentargets_mcp.server

{
  "mcpServers": {
    "opentargets": {
      "command": "uv",
      "args": ["run", "python", "-m", "opentargets_mcp.server", "--transport", "stdio"]
    }
  }
}

FAQ

支持哪些传输模式？

服务器支持 stdio（默认）、SSE 和 HTTP 传输模式，由 FastMCP 驱动。

我可以过滤工具返回的数据吗？

可以，许多核心工具接受可选的 'fields' 参数来过滤响应负载并减少令牌开销。

opentargets-mcp 对比