microbeFunction_mcp
Click on "Install 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., "@microbeFunction_mcpFind Clostridium baratii in human gut and analyze its KEGG module completeness"
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.
microbeFunction_mcp
微生物功能分析 MCP 工具包
支持mgnify_genomes数据库所有菌种(包含人肠道,口腔,阴道;小鼠肠道;海洋淤泥;土壤;根际;牛羊瘤胃等)的基因组信息下载和查询 支持KEGG所有数据库查询和功能注释,代谢模块完整度分析,构建细菌和古菌KEGG pathway/module的白名单及只在真核中出现的terms的黑名单及关键词
概览
工具包 | 功能 | 端口 |
| KEGG REST API + 代谢模块完整度分析 + COG数据库(依赖 | 8791 |
| MGnify 物种索引检索 + 注释文件按需下载 | 8792 |
| 统一 FastAPI 部署层,同时挂载两个 MCP | 8788 |
Related MCP server: Ensembl MCP Server
部署
1. 安装依赖
pip install uv
uv venv .venv --python=3.13
# Windows: .venv\Scripts\activate
# Linux/macOS: source .venv/bin/activate
uv sync2. 配置
cp default.conf.toml local.conf.toml
# 按需修改 local.conf.toml 中的端口等配置3. 启动统一服务
uv run -m deploy.web启动后:
KEGG MCP:
http://127.0.0.1:8788/kegg_mcp/mcp/MGnify MCP:
http://127.0.0.1:8788/mgnify_mcp/mcp/服务列表:
http://127.0.0.1:8788/api/list_mcps
4. 单独启动某个 MCP
# KEGG (端口 8791)
uv run -m tools.kegg.deploy
# MGnify (端口 8792)
uv run -m tools.mgnify.deploy典型工作流
search_species (mgnify) → fetch_annotations (mgnify) → kegg_module_completeness (kegg)
找到物种 MAG 下载 eggNOG/GFF 注释 分析代谢模块完整度使用示例:生成 Clostridium baratii 功能画像
步骤 1:搜索物种
uv run -m tools.mgnify search --biome human-gut --query "Clostridium baratii"输出示例:
{
"items": [
{
"species_rep": "MGYG000000064",
"species_name": "Clostridium baratii",
"completeness": 99.19,
"contamination": 1.61,
"genome_count": 12
}
]
}步骤 2:下载注释
uv run -m tools.mgnify fetch --species-rep MGYG000000064 --biome human-gut --roles eggnog_tsv,gff注释文件会保存在 downloads/MGYG000000064/genome/ 目录下。
步骤 3:分析代谢模块完整度
uv run -m tools.kegg analyze \
--annotation-file downloads/MGYG000000064/genome/MGYG000000064_eggNOG.tsv \
--kegg-column KEGG_ko \
--output downloads/MGYG000000064/genome/MGYG000000064_module_completeness.tsv输出示例:
output=downloads/MGYG000000064/genome/MGYG000000064_module_completeness.tsv
unique_ko_count=1384 modules_with_any_hit=180 modules_above_threshold=180步骤 4:解读结果
功能分类 | 完整模块数/总模块数 |
Carbohydrate metabolism | 8/30 |
Amino acid metabolism | 12/39 |
Energy metabolism | 4/23 |
Nucleotide metabolism | 6/10 |
Glycan metabolism | 6/15 |
Cofactor and vitamin metabolism | 7/38 |
Lipid metabolism | 3/9 |
代表性完整模块:
M00001: 糖酵解 (Embden-Meyerhof pathway)
M00632: 半乳糖降解 (Leloir pathway)
M00579: 乙酸生成 (磷酸乙酰转移酶-乙酸激酶)
M00651: 万古霉素耐药 (D-Ala-D-Lac type)
M00122: 钴胺素生物合成 (维生素B12)
M00924: 钴胺素生物合成 (厌氧途径)
部分完整模块:
M00003: 糖酵解 (78.57%)
M00010: 乙醇发酵 (66.67%)
M00009: 乳酸发酵 (50.0%)
基因组概览:
总基因数:2,893
有 KO 注释的基因:1,647 (56%)
COG 分类:碳水化合物代谢 (229)、氨基酸代谢 (191)、能量代谢 (171)
CAZy 酶:糖基转移酶 (GT) 22 个、糖苷水解酶 (GH) 16 个
CLI 用法
# KEGG 模块完整度分析
uv run -m tools.kegg analyze --annotation-file downloads/MGYG000000238/genome/MGYG000000238_gene_annotations.tsv
# KEGG 批处理
uv run -m tools.kegg batch --manifest manifest.tsv --jobs 4
# MGnify 物种搜索
uv run -m tools.mgnify search --biome human-gut --query "Enterobacter kobei"
# MGnify 注释下载
uv run -m tools.mgnify fetch --species-rep MGYG000000238 --biome human-gut --roles eggnog_tsv数据路径
MGnify 索引:
data/mgnify/MGnify 注释缓存:
downloads/{species_rep}/genome/KEGG allowlist 数据:
tools/kegg/data/COG 目录:
tools/kegg/data/COG.csv
可通过环境变量 MGNIFY_DATA_DIR 覆盖 MGnify 索引目录。
项目结构
microbeFunction_mcp/
├── tools/
│ ├── kegg/ # KEGG MCP
│ │ ├── server.py # FastMCP server
│ │ ├── kegg_api.py # KEGG REST API 封装
│ │ ├── module_completeness.py
│ │ ├── cog_store.py
│ │ ├── ko_input.py
│ │ ├── allowlist_sources.py
│ │ ├── cli.py
│ │ ├── deploy.py # 单独部署入口
│ │ └── data/ # allowlist 等数据文件
│ └── mgnify/ # MGnify MCP
│ ├── server.py
│ ├── fetch.py
│ ├── index_store.py
│ ├── cli.py
│ ├── deploy.py
│ ├── download_species_annotations.py
│ ├── download_human_gut_metadata.py
│ ├── list_mgnify_folders.py
│ └── build_mgnify_index.py
├── deploy/
│ ├── web.py # 统一 FastAPI 入口
│ └── config.py # 配置加载
├── tests/
├── data/
│ └── mgnify/ # 共享数据
├── pyproject.toml
├── default.conf.toml
└── .gitignoreCursor / Claude Desktop 配置
{
"mcpServers": {
"kegg_mcp": {
"url": "http://127.0.0.1:8788/kegg_mcp/mcp/",
"transport": "streamable_http"
},
"mgnify_mcp": {
"url": "http://127.0.0.1:8788/mgnify_mcp/mcp/",
"transport": "streamable_http"
}
}
}This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Miooooooo/microbeFunction_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server