NCBI Datasets MCP Server

NCBI Datasets MCP Server

Provides comprehensive access to the NCBI Datasets API, enabling genomic, taxonomic, and biological data operations through 31 specialized tools.

Category
访问服务器

README

NCBI Datasets MCP Server Logo

Unofficial NCBI Datasets MCP Server

A Model Context Protocol (MCP) server that provides comprehensive access to the NCBI Datasets API. This server enables seamless integration with NCBI's vast collection of genomic, taxonomic, and biological data through 31 specialized tools.

Developed by Augmented Nature

Features

  • 31 comprehensive tools covering all major NCBI Datasets functionality
  • 9 organized categories of biological data operations
  • Resource templates for direct URI-based data access
  • Full TypeScript implementation with proper error handling
  • Rate limiting and caching for optimal performance
  • Environment variable configuration for API keys

Installation

npm install
npm run build

Configuration

Environment Variables

  • NCBI_API_KEY (optional): Your NCBI API key for higher rate limits and priority access

MCP Configuration

Add to your MCP settings:

{
  "mcpServers": {
    "ncbi-datasets-server": {
      "command": "node",
      "args": ["/path/to/ncbi-datasets-server/build/index.js"],
      "env": {
        "NCBI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Available Tools

🧬 Genome Operations

  • search_genomes - Search genome assemblies by organism, keywords, or criteria
  • get_genome_info - Get detailed information for a specific genome assembly
  • get_genome_summary - Get summary statistics for a genome assembly

🧬 Gene Operations

  • search_genes - Search genes by symbol, name, organism, or location
  • get_gene_info - Get detailed information for a specific gene
  • get_gene_sequences - Retrieve sequences for a specific gene

🏷️ Taxonomy Operations

  • search_taxonomy - Search taxonomic information by organism name
  • get_taxonomy_info - Get detailed taxonomic information for a taxon
  • get_organism_info - Get organism-specific information and datasets

🏗️ Assembly Operations

  • search_assemblies - Search genome assemblies with detailed filtering
  • get_assembly_info - Get detailed metadata and statistics for assemblies
  • get_assembly_reports - Get assembly quality reports and validation info
  • download_genome_data - Get download URLs for genome data files
  • batch_assembly_info - Get information for multiple assemblies

🦠 Virus Operations

  • search_virus_genomes - Search viral genome assemblies
  • get_virus_info - Get detailed information for viral genomes

🧪 Protein Operations

  • search_proteins - Search protein sequences by name or function
  • get_protein_info - Get detailed information for specific proteins

📝 Annotation Operations

  • get_genome_annotation - Get annotation information for assemblies
  • search_genome_features - Search for specific genomic features

🔬 Comparative Genomics

  • compare_genomes - Compare two or more genome assemblies
  • find_orthologs - Find orthologous genes across organisms

🧬 Sequence Operations

  • get_sequence_data - Retrieve sequence data for genomes/genes/proteins
  • blast_search - Perform BLAST search against NCBI databases

🌳 Phylogenetic Operations

  • get_phylogenetic_tree - Get phylogenetic tree data for organisms
  • get_taxonomic_lineage - Get complete taxonomic lineage

📊 Statistics Operations

  • get_database_stats - Get statistics about NCBI Datasets content
  • search_by_bioproject - Search datasets by BioProject accession
  • search_by_biosample - Search datasets by BioSample accession

✅ Quality Control

  • get_assembly_quality - Get quality metrics for genome assemblies
  • validate_sequences - Validate sequence data and check for issues

Usage Examples

Genome Analysis

// Search for E. coli genomes
{
  "tool": "search_genomes",
  "arguments": {
    "tax_id": 511145,
    "assembly_level": "complete",
    "max_results": 10
  }
}

// Get detailed genome information
{
  "tool": "get_genome_info",
  "arguments": {
    "accession": "GCF_000005845.2",
    "include_annotation": true
  }
}

// Get genome summary statistics
{
  "tool": "get_genome_summary",
  "arguments": {
    "accession": "GCF_000005845.2"
  }
}

Gene Research

// Search for BRCA1 gene
{
  "tool": "search_genes",
  "arguments": {
    "gene_symbol": "BRCA1",
    "organism": "Homo sapiens",
    "max_results": 5
  }
}

// Get detailed gene information
{
  "tool": "get_gene_info",
  "arguments": {
    "gene_id": 672,
    "include_sequences": true
  }
}

// Get gene sequences
{
  "tool": "get_gene_sequences",
  "arguments": {
    "gene_id": 672,
    "sequence_type": "transcript"
  }
}

Taxonomic Analysis

// Search taxonomy by organism name
{
  "tool": "search_taxonomy",
  "arguments": {
    "query": "Escherichia coli",
    "max_results": 10
  }
}

// Get detailed taxonomic information
{
  "tool": "get_taxonomy_info",
  "arguments": {
    "tax_id": 511145,
    "include_lineage": true
  }
}

// Get organism information
{
  "tool": "get_organism_info",
  "arguments": {
    "organism": "Escherichia coli"
  }
}

Assembly Operations

// Search assemblies with filtering
{
  "tool": "search_assemblies",
  "arguments": {
    "query": "human",
    "assembly_level": "chromosome",
    "assembly_source": "refseq",
    "max_results": 20
  }
}

// Get assembly information
{
  "tool": "get_assembly_info",
  "arguments": {
    "assembly_accession": "GCF_000001405.40",
    "include_annotation": true
  }
}

// Batch assembly lookup
{
  "tool": "batch_assembly_info",
  "arguments": {
    "accessions": ["GCF_000001405.40", "GCF_000005825.2", "GCF_000002305.1"]
  }
}

Comparative Genomics

// Compare multiple genomes
{
  "tool": "compare_genomes",
  "arguments": {
    "accessions": ["GCF_000005845.2", "GCF_000001405.40"],
    "comparison_type": "basic_stats",
    "include_orthologs": true
  }
}

// Find orthologous genes
{
  "tool": "find_orthologs",
  "arguments": {
    "gene_symbol": "BRCA1",
    "source_organism": "Homo sapiens",
    "target_organisms": ["Mus musculus", "Rattus norvegicus"],
    "similarity_threshold": 80
  }
}

Virus Research

// Search viral genomes
{
  "tool": "search_virus_genomes",
  "arguments": {
    "virus_name": "SARS-CoV-2",
    "host": "Homo sapiens",
    "max_results": 50
  }
}

// Get viral genome information
{
  "tool": "get_virus_info",
  "arguments": {
    "accession": "NC_045512.2",
    "include_proteins": true,
    "include_metadata": true
  }
}

Resource Templates

The server provides resource templates for direct data access:

  • ncbi://genome/{accession} - Complete genome assembly information
  • ncbi://gene/{gene_id} - Gene information with annotations
  • ncbi://taxonomy/{tax_id} - Taxonomic classification and lineage
  • ncbi://assembly/{assembly_accession} - Assembly metadata and statistics
  • ncbi://search/{data_type}/{query} - Search results for specified queries

API Rate Limits

  • Without API key: 3 requests per second
  • With API key: 10 requests per second with priority access

To obtain an API key, visit: https://www.ncbi.nlm.nih.gov/account/settings/

Error Handling

The server implements comprehensive error handling:

  • Network errors: Automatic retry with exponential backoff
  • Rate limiting: Intelligent request queuing and throttling
  • Invalid parameters: Clear validation error messages
  • API errors: Detailed error reporting with context

Data Sources

This server accesses data from:

  • NCBI Datasets API v2: Primary genomic and assembly data
  • NCBI Taxonomy: Taxonomic classifications and lineages
  • NCBI Gene: Gene annotations and sequences
  • NCBI Assembly: Assembly metadata and quality metrics
  • NCBI BioProject/BioSample: Project and sample information

License

MIT License - see LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit issues, feature requests, or pull requests.

Support

For issues related to:

  • Server functionality: Open an issue in this repository
  • NCBI data: Consult NCBI Datasets documentation
  • API access: Contact NCBI support for API-related questions

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