genome-mcp
Genome MCP is an intelligent genomic data server providing high-quality gene information, homologous gene analysis, evolutionary research, and pathway enrichment through the MCP protocol, powered by authoritative databases (NCBI Gene, Ensembl, KEGG).
Core Capabilities:
Gene & Protein Data - Smart retrieval with automatic query type recognition (gene symbols, IDs, protein details, chromosomal regions like chr17:7565097-7590856), batch processing with parallel execution, and multiple output formats (simple, detailed, raw)
Intelligent Search - Natural language semantic search with context-awareness (genomics, proteomics, pathway), smart result ranking and filtering
Evolutionary & Comparative Analysis - Cross-species homologous gene queries (253+ species via Ensembl), phylogenetic profiling, conservation scoring, and domain information integration
KEGG Pathway Enrichment - Statistical pathway over-representation analysis with FDR correction, multi-organism support (human, mouse, rat, etc.), and customizable significance thresholds
Advanced Query Features - Complex batch queries with custom strategies (parallel/sequential), flexible filtering, result pagination, and optimized execution paths
Integration & Performance - Multiple transport protocols (STDIO, HTTP, SSE), asynchronous architecture for high-performance processing, compatible with MCP clients (Claude Desktop, Continue.dev, Cursor, Cline, Windsurf), and scientific reliability with no simulated data
Distributed as a Python package through PyPI, providing intelligent genome data services with gene information queries, homolog analysis, and evolutionary research capabilities.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@genome-mcp show me the homologous genes for TP53 in mice"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Genome MCP
🧬 智能基因组数据服务器 - 通过MCP协议提供高质量的基因信息查询、同源基因分析和进化研究功能。可在 Glama MCP平台 发现和快速配置。
1. 🚀 核心特性
🧬 基因信息查询: 基于NCBI Gene数据库的准确基因信息
🔄 同源基因分析: 基于Ensembl API的跨物种同源基因查询(253+ TP53同源基因)
🧬 进化分析: 系统发育关系构建和保守性分析
🔍 语义搜索: 理解查询意图的智能搜索功能
📊 批量处理: 优化的并发查询,支持大规模数据分析
🌐 多传输模式: 支持STDIO、HTTP、SSE传输协议
⚡ 异步架构: 高性能异步处理架构
🔬 科学可靠: 基于权威数据库,无模拟数据,完全科学可信
Related MCP server: GeneOntology MCP Server
2. 安装
推荐使用现代化的 uv 包管理器以获得更快的安装速度:
# 使用uvx直接运行(推荐)
uvx genome-mcp
# 或添加到项目
uv add genome-mcp传统方式安装:
pip install genome-mcp3. 🛠️ MCP 接入配置
3.1 Claude Desktop
编辑配置文件:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
推荐使用 uvx 运行:
{
"mcpServers": {
"genome-mcp": {
"command": "uvx",
"args": ["genome-mcp"],
"env": {}
}
}
}或使用传统方式:
{
"mcpServers": {
"genome-mcp": {
"command": "python",
"args": ["-m", "genome_mcp"],
"env": {}
}
}
}或使用 uv run:
{
"mcpServers": {
"genome-mcp": {
"command": "uv",
"args": ["run", "-m", "genome_mcp"],
"env": {}
}
}
}3.2 Continue.dev
在 VS Code 的 Continue.dev 扩展配置中:
{
"mcpServers": {
"genome-mcp": {
"command": "uvx",
"args": ["genome-mcp"]
}
}
}3.3 Cursor (VS Code 扩展)
在 Cursor 设置中添加:
{
"mcpServers": {
"genome-mcp": {
"command": "uvx",
"args": ["genome-mcp"],
"env": {
"GENOME_MCP_LOG_LEVEL": "info"
}
}
}
}3.4 Cline (Claude for VS Code)
在 Cline 设置文件中:
{
"mcpServers": {
"genome-mcp": {
"command": "uvx",
"args": ["genome-mcp"],
"timeout": 30000
}
}
}3.5 其他支持 MCP 的客户端
Windsurf: 使用与 Claude Desktop 相同的配置格式
OpenHands: 在 config.json 中添加服务器配置
Custom MCP Client: 参考下面的 Python 示例
3.6 自定义 MCP 客户端
使用 stdio 传输:
import subprocess
import json
# 启动 MCP 服务器
process = subprocess.Popen(
["python", "-m", "genome_mcp"],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
text=True
)
# 发送初始化消息
init_message = {
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2024-11-05",
"capabilities": {},
"clientInfo": {"name": "test-client", "version": "1.0.0"}
}
}
process.stdin.write(json.dumps(init_message) + "\n")
response = process.stdout.readline()
print("Server response:", response)4. 🔧 API 功能
4.1 可用工具
get_data - 智能数据获取
支持基因符号、ID、区域搜索、同源基因查询
自动类型识别和查询优化
批量查询支持
advanced_query - 高级批量查询
复杂查询条件组合
批量处理优化
自定义输出格式
smart_search - 语义搜索
自然语言查询理解
智能结果排序
上下文感知搜索
kegg_pathway_enrichment_tool - KEGG通路富集分析 🆕
基因列表在KEGG通路中的富集分析
超几何分布检验计算统计显著性
FDR多重检验校正
支持人类、小鼠、大鼠等多种模式生物
4.2 使用示例
import asyncio
from genome_mcp import get_data, advanced_query, smart_search
async def main():
# 获取基因信息
gene_info = await get_data("TP53")
print("Gene info:", gene_info)
# 区域搜索
region_data = await get_data("chr17:7565097-7590856", query_type="region")
print("Region data:", region_data)
# 批量查询
batch_results = await get_data(["TP53", "BRCA1", "EGFR"], query_type="gene")
print("Batch results:", batch_results)
# 语义搜索
search_results = await smart_search("tumor suppressor genes involved in cancer")
print("Search results:", search_results)
# 高级查询
advanced_results = await advanced_query(
query="cancer genes",
query_type="search",
database="gene",
max_results=20
)
print("Advanced results:", advanced_results)
# KEGG通路富集分析
kegg_results = await kegg_pathway_enrichment_tool(
gene_list=["7157", "672", "675"], # TP53, BRCA1, BRCA2的Entrez ID
organism="hsa",
pvalue_threshold=0.05,
min_gene_count=2
)
print("KEGG enrichment results:", kegg_results)
asyncio.run(main())5. 📋 响应格式
所有API响应都遵循统一的JSON格式,包含 success、data 和 query_info 字段。
示例响应:
{
"success": true,
"data": {
"gene_info": {
"uid": "7157",
"name": "TP53",
"description": "tumor protein p53"
}
},
"query_info": {
"query": "TP53",
"query_type": "gene"
}
}6. 💻 命令行使用
# 直接运行(推荐)
uvx genome-mcp
# 开发模式运行
uv run -m genome_mcp
# HTTP 服务器模式
uv run -m genome_mcp --port 8080
# 查看帮助
uv run -m genome_mcp --help7. 📋 更新日志
详细的版本更新记录请查看 CHANGELOG.md
8. 📚 依赖
详细的依赖信息和版本要求请查看 pyproject.toml
Python 版本要求:>= 3.11
9. 🏗️ 开发
git clone https://github.com/gqy20/genome-mcp
cd genome-mcp
pip install -e ".[dev]"
make test
make lint9.1 开发命令
make install # 安装开发依赖
make format # 格式化代码
make lint # 代码质量检查
make test # 运行测试
make check # 完整检查
make build # 构建包10. 📄 许可证
本项目采用 MIT License 开源许可证。
© 2025 gqy20
11. 🤝 贡献
欢迎提交 Issue 和 Pull Request!
12. 📞 支持
Genome MCP - 让基因组数据访问更简单、更智能!
Available Tools
6 toolsadvanced_queryA
高级批量查询 - 支持复杂查询策略
Args: queries: 查询列表,每个元素包含 {"query": str, "type": str} strategy: 执行策略(parallel/sequential) delay: 查询间隔(秒)
Returns: 批量查询结果
Examples: advanced_query([ {"query": "TP53", "type": "info"}, {"query": "BRCA1", "type": "info"}, {"query": "cancer", "type": "search"} ])
Inputs: queries (required), strategy, delay. Returns: 高级查询结果类型
analyze_gene_evolutionB
基因进化分析工具 - MCP接口包装
Args: gene_symbol: 基因符号(如 TP53, BRCA1) target_species: 目标物种列表(如 ["mouse", "rat", "zebrafish"]) analysis_level: 分析层级(如 Eukaryota, Metazoa, Vertebrata) include_sequence_info: 是否包含序列信息
Returns: 进化分析结果
Examples: # 分析 TP53 在哺乳动物中的进化 analyze_gene_evolution("TP53", ["human", "mouse", "rat", "dog"])
Inputs: gene_symbol (required), target_species, analysis_level, include_sequence_info. Returns: 进化分析结果类型
build_phylogenetic_profileB
系统发育图谱构建工具 - MCP接口包装
Args: gene_symbols: 基因符号列表 species_set: 物种集合(默认包含常用模式生物) include_domain_info: 是否包含结构域信息
Returns: 系统发育图谱数据
Examples: # 分析p53家族在脊椎动物中的分布 build_phylogenetic_profile(["TP53", "TP63", "TP73"], ["human", "mouse", "zebrafish"])
Inputs: gene_symbols (required), species_set, include_domain_info. Returns: 系统发育图谱结果类型
get_dataA
智能数据获取接口 - 统一处理所有查询类型
自动识别查询类型:
"TP53" → 基因信息查询
"P04637" → 蛋白质详细信息查询
"cancer" → 基因搜索
"protein kinase" → 蛋白质功能搜索
"chr17:7565097-7590856" → 区域搜索
"TP53, BRCA1" → 批量基因信息
"breast cancer genes" → 智能搜索
"TP53 homologs" → 同源基因查询
"evolutionary conservation" → 进化分析查询
Args: query: 查询内容(可以是基因ID、蛋白质ID、搜索词、区域、ID列表、进化相关查询) query_type: 查询类型(auto/info/search/region/protein/gene_protein/ortholog/evolution) data_type: 数据类型(gene/protein/gene_protein/ortholog/evolution) format: 返回格式(simple/detailed/raw) species: 物种(默认:human,支持9606/human/mouse/rat等) max_results: 最大结果数(默认:20)
Returns: 查询结果字典,包含基因和/或蛋白质信息
Examples: # 基因信息查询 get_data("TP53") get_data("TP53", format="detailed")
# 批量查询
get_data(["TP53", "BRCA1", "BRCA2"])
# 区域搜索
get_data("chr17:7565097-7590856")
# 蛋白质查询
get_data("P04637", data_type="protein")
# 基因-蛋白质整合查询
get_data("TP53", data_type="gene_protein")
# 蛋白质功能搜索
get_data("tumor suppressor", data_type="protein")Inputs: query (required), query_type, data_type, format, +2 more. Returns: 通用工具返回类型
kegg_pathway_enrichmentA
KEGG通路富集分析工具 - MVP版本
分析基因列表在KEGG通路中的富集情况,识别显著相关的生物学通路
Args: gene_list: 基因列表(如 ["TP53", "BRCA1", "BRCA2"]) organism: 生物体代码(默认 "hsa" 人类) pvalue_threshold: p值显著性阈值(默认 0.05) min_gene_count: 通路中最小基因数量(默认 2)
Returns: 通路富集分析结果,包含: - 显著富集的通路列表 - p值和FDR校正后的统计显著性 - 富集倍数和基因数量信息 - 分析参数和元数据
Examples: # 分析癌症相关基因的通路富集 kegg_pathway_enrichment(["TP53", "BRCA1", "BRCA2", "EGFR"])
# 分析小鼠基因的通路富集
kegg_pathway_enrichment(["Trp53", "Brca1"], organism="mmu")
# 使用更严格的显著性阈值
kegg_pathway_enrichment(["TP53", "BRCA1"], pvalue_threshold=0.01)Inputs: gene_list (required), organism, pvalue_threshold, min_gene_count. Returns: KEGG通路富集分析结果类型
smart_searchB
智能语义搜索 - 理解自然语言描述并执行相应查询
语义理解示例:
"breast cancer genes on chromosome 17" → 查找17号染色体上的乳腺癌基因
"TP53 protein interactions" → 查找TP53蛋白相互作用
"tumor suppressor genes" → 查找肿瘤抑制基因
"genes related to DNA repair" → 查找DNA修复相关基因
Args: description: 自然语言描述 context: 搜索上下文(genomics/proteomics/pathway) filters: 过滤条件 max_results: 最大结果数
Returns: 智能搜索结果
Examples: smart_search("breast cancer genes on chromosome 17") smart_search("TP53 protein interactions", context="proteomics") smart_search("DNA repair genes", filters={"species": "human"})
Inputs: description (required), context, filters, max_results. Returns: 搜索结果类型
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Significant overlap exists: get_data is a super-tool that handles batch queries (like advanced_query), semantic search (like smart_search), and even evolution queries (overlapping with analyze_gene_evolution). This makes it difficult for an agent to know which tool to use.
Names are all lowercase with underscores, but some are verb_noun (analyze_gene_evolution, get_data) while others are adjective+noun (advanced_query, smart_search) or noun phrases (kegg_pathway_enrichment). The pattern is inconsistent.
6 tools is well-scoped for a genomics data server covering querying, evolution, and pathway enrichment. Each tool has a clear purpose despite overlaps.
The toolset covers data retrieval and some analysis (evolution, enrichment), but lacks common genomics operations like sequence alignment, variant analysis, or expression analysis. Gaps exist but core data access is handled.
Maintenance
Related MCP Connectors
MyGene.info MCP. Docs: https://docs.mygene.info/en/latest/
MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.
NCBI Datasets — the US National Library of Medicine's genome, gene and taxonomy reference service…
QuickGO (EBI) MCP — Gene Ontology browser.
Related MCP Servers
- AlicenseAqualityDmaintenanceA comprehensive Model Context Protocol (MCP) server that provides access to the Ensembl REST API for genomic data, comparative genomics, and biological annotations.194MIT
- AlicenseBqualityDmaintenanceA comprehensive Model Context Protocol server for accessing Gene Ontology (GO) data, enabling AI systems to perform ontology-based analysis, gene annotation research, and functional enrichment studies.47MIT
- AlicenseBqualityDmaintenanceMCP server that interfaces with the NCBI Entrez API to fetch detailed information about genes and proteins, enabling gene searches, gene/protein metadata retrieval, and symbol searching with organism filtering.43MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for the gget bioinformatics library that enables AI assistants to perform complex genomics queries, including gene sequence retrieval, BLAST alignments, and protein structure predictions.33MIT