LG

longevity-genie/biothings-mcp

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

37 stars 10 forks 质量 63 趋势 12MIT

longevity-genie/biothings-mcp 是从 https://github.com/longevity-genie/biothings-mcp. 导入的 MCP 服务器候选服务器。

概览

longevity-genie/biothings-mcp 是从 https://github.com/longevity-genie/biothings-mcp. 导入的 MCP 服务器候选服务器。

概述(AI 翻译)

MCP(模型上下文协议)服务器用于 Biothings.io

该服务器实现了BioThings的模型上下文协议(MCP),为访问和操作生物医学数据提供了标准化接口。MCP使AI助手和代理能够通过结构化接口访问权威数据源的专业生物医学知识。支持的BioThings数据源包括:

如果你想更了解什么是模型上下文协议以及如何更高效地使用它,可以参加深度学习AI课程,或者在YouTube上搜索MCP视频。

关于MCP(模型上下文协议)

MCP是一种连接人工智能系统与专业领域知识之间的协议。它能够实现:

  • 结构化访问:直接连接权威生物医学数据源
  • 自然语言查询:与专业数据库的简化交互
  • 类型安全:通过生物物类型客户端实现强类型和验证
  • AI集成:与AI助手和代理无缝集成

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

biothings-mcp

MCP (Model Context Protocol) server for Biothings.io

This server implements the Model Context Protocol (MCP) for BioThings, providing a standardized interface for accessing and manipulating biomedical data. MCP enables AI assistants and agents to access specialized biomedical knowledge through structured interfaces to authoritative data sources. Supported BioThings data sources include:

If you want to understand more what is Model Context Protocol and how to use it more efficiently you can take DeepLearning AI Course or just search for MCP videos on YouTube.

About MCP (Model Context Protocol)

MCP is a protocol that bridges the gap between AI systems and specialized domain knowledge. It enables:

  • Structured Access: Direct connection to authoritative biomedical data sources
  • Natural Language Queries: Simplified interaction with specialized databases
  • Type Safety: Strong typing and validation through biothings-typed-client
  • AI Integration: Seamless integration with AI assistants and agents

Available API Interfaces

This server provides dedicated API interfaces for different BioThings data types, leveraging the biothings-typed-client library. These interfaces are implemented using the following tool handlers:

  • Gene Interface: GeneTools (wraps GeneClientAsync)
  • Variant Interface: VariantTools (wraps VariantClientAsync)
  • Chemical Interface: ChemTools (wraps ChemClientAsync)
  • Taxon Interface: TaxonTools (wraps TaxonClientAsync)
  • Download Interface: DownloadTools (provides file download and sequence analysis capabilities)

Local File Saving Features

The server includes local file saving capabilities through the DownloadTools interface, which provides:

Download Tools

  • download_entrez_data: Download data from NCBI Entrez databases (returns content as string)
  • download_entrez_data_local: Download data from NCBI Entrez databases and save to local file

Output Directory Management

  • Default Location: Files are saved to biothings_output/ directory in the current working directory
  • Custom Location: Use --output-dir parameter to specify a custom output directory
在 GitHub 查看完整 README

安装

uvx --version
新手?先看 mcpskill.org 教程 →