BioOntology MCP Server

BioOntology MCP Server

A production-ready Model Context Protocol (MCP) server that provides comprehensive access to the BioOntology API for searching, annotating, and exploring over 1,200 biological ontologies.

Category
访问服务器

README

Logo

Unofficial BioOntology MCP Server

A production-ready Model Context Protocol (MCP) server that provides comprehensive access to the BioOntology API for searching, annotating, and exploring over 1,200 biological ontologies.

Features

Search & Discovery

  • search_terms - Search across ontology terms with advanced filtering options
  • search_properties - Search ontology properties by labels and IDs
  • search_ontologies - Find ontologies by name, description, or domain
  • get_ontology_info - Get detailed information about specific ontologies

Text Analysis

  • annotate_text - Analyze text and identify relevant ontology terms
  • recommend_ontologies - Get ontology recommendations for text or keywords
  • batch_annotate - Process multiple texts for annotation efficiently

Ontology Navigation

  • get_class_info - Get detailed information about ontology classes

Analytics & Metadata

  • get_ontology_metrics - Get usage statistics and quality metrics
  • get_analytics_data - Get visitor statistics and popularity trends

Installation

  1. Clone or download this server
  2. Install dependencies:
    npm install
    
  3. Build the server:
    npm run build
    

Configuration

You need a BioOntology API key to use this server. Get one from BioPortal:

  1. Create an account at https://bioportal.bioontology.org/
  2. Generate an API key from your account settings
  3. Set the environment variable:
    export BIOONTOLOGY_API_KEY=your_api_key_here
    

Usage

Running the Server

node build/index.js

The server runs on stdio and implements the MCP protocol for communication with MCP-compatible clients.

Resource Templates

The server provides several resource templates for direct data access:

  • bioontology://ontology/{acronym} - Complete ontology information
  • bioontology://class/{ontology}/{class_id} - Ontology class details
  • bioontology://search/{query} - Term search results
  • bioontology://annotations/{text} - Text annotation results
  • bioontology://recommendations/{input} - Ontology recommendations
  • bioontology://analytics/{ontology} - Analytics data

Example Tool Calls

Search for terms:

{
  "tool": "search_terms",
  "arguments": {
    "query": "diabetes",
    "ontologies": "NCIT,DOID",
    "require_definitions": true,
    "pagesize": 10
  }
}

Annotate text:

{
  "tool": "annotate_text",
  "arguments": {
    "text": "The patient has diabetes mellitus and hypertension",
    "ontologies": "NCIT,DOID,HP",
    "longest_only": true
  }
}

Get ontology recommendations:

{
  "tool": "recommend_ontologies",
  "arguments": {
    "input": "cancer treatment protocols",
    "input_type": 1,
    "output_type": 1
  }
}

Batch annotate multiple texts:

{
  "tool": "batch_annotate",
  "arguments": {
    "texts": ["diabetes mellitus", "cardiac arrest", "lung cancer"],
    "ontologies": "NCIT",
    "longest_only": true
  }
}

Supported Ontologies

The server works with all ontologies available in BioPortal (1,200+), including:

Medical/Clinical:

  • NCIT - NCI Thesaurus (cancer terminology)
  • DOID - Disease Ontology
  • HP - Human Phenotype Ontology
  • MESH - Medical Subject Headings

Biological/Chemical:

  • GO - Gene Ontology
  • UBERON - Anatomy ontology
  • CHEBI - Chemical entities of biological interest

And 1,190+ more specialized ontologies

Integration with MCP Clients

This server is compatible with any MCP-enabled client. Popular options include:

  • Claude Desktop - Add to your MCP configuration
  • VSCode Extensions - Use with MCP-compatible extensions
  • Custom Applications - Integrate via the MCP protocol

MCP Configuration Example

Add to your MCP client configuration:

{
  "servers": {
    "bioontology": {
      "command": "node",
      "args": ["/path/to/bioontology-server/build/index.js"],
      "env": {
        "BIOONTOLOGY_API_KEY": "your_api_key_here"
      }
    }
  }
}

Advanced Features

Input Validation

  • Comprehensive parameter validation with proper error messages
  • Type checking for all inputs
  • Range validation for numeric parameters
  • Enum validation for restricted values

Error Handling

  • Graceful handling of API errors
  • Structured error responses
  • Network timeout management
  • Authentication error reporting

Performance

  • Efficient API request handling
  • Proper timeout management
  • Memory usage optimization
  • Concurrent request support

API Documentation

For detailed BioOntology API documentation, see: https://data.bioontology.org/documentation

Production Use

This server has been thoroughly tested and is ready for production use. It provides:

  • Reliable API integration with robust error handling
  • Comprehensive input validation for all tools
  • Full MCP protocol compliance for seamless integration
  • Support for 1,200+ ontologies across all biological domains
  • High performance with optimized response times

License

MIT License - see LICENSE file for details.

Citation

If you use this project in your research or publications, please cite it as follows:

<pre><code>@misc{yourproject2025, author = {Moudather Chelbi}, title = {Augmented Nature BioOntology MCP Server}, year = {2025}, howpublished = {https://github.com/Augmented-Nature/BioOntology-MCP-Server}, }</code></pre>

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选