Skip to content

Latest commit

 

History

211 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

BioMCP — 生物信息孊 MCP 服务噚 / Bioinformatics MCP Server

BioMCP is an open-source MCP server that connects any AI assistant directly to 43 open bioinformatics databases — zero config, no API keys. Literature, sequences, BLAST, structures, enrichment, annotations, genomes, interactions, pathways, variants, population frequencies, methylation QTLs, tissue expression, drug targets, compounds, single-cell, glycomics, metabolomics, lipidomics, microbiome, plants, model organisms, proteomics and more.

BioMCP 是䞀䞪匀源的 MCP 服务噚让任意 AI 助手零配眮盎连 43 䞪公匀生物数据库——文献、序列、比对、结构、富集、泚释、基因组、互䜜、通路、变匂、人矀频率、甲基化 QTL、衚观遗䌠、组织衚蟟、药物靶点、化合物、单细胞、糖组孊、代谢组孊、脂莚组孊、埮生物组、怍物、暡匏生物、蛋癜莚组孊等党流皋。

MCP PyPI Tools Databases Python License Platform


特性 / Features

标准 MCP 协议 / Standard MCP protocol — Based on official MCP SDK with stdio transport, compatible with all MCP clients 基于官方 MCP SDKstdio 䌠蟓兌容所有 MCP 客户端

83 䞪工具 · 43 䞪数据库 / 83 tools · 43 databases — Covers literature → sequences → structures → functions → interactions → pathways → variants → population frequency → methylation → tissue expression → drug targets → drugs → single-cell → glycomics → metabolomics → lipidomics → microbiome → plants → model organisms → proteomics → intelligent analysis 芆盖文献→序列→结构→功胜→互䜜→通路→变匂→人矀频率→甲基化→组织衚蟟→药物靶点→药物→单细胞→糖组孊→代谢组孊→脂莚组孊→埮生物组→怍物→暡匏生物→蛋癜莚组孊→智胜分析党流皋

零配眮䜿甚 / Zero-config — pip install biomcp-server one command, no database setup, no API keys required pip install biomcp-server 䞀条呜什无需数据库、无需密钥

数据公匀权嚁 / Authoritative public data — All from official APIs: NCBI / RCSB / UniProt / Ensembl / EBI / STRING / KEGG / GlyGen / Reactome / OpenAlex, etc. 党郚来自 NCBI / RCSB / UniProt / Ensembl / EBI / STRING / KEGG / GlyGen / Reactome / OpenAlex 等官方 API

智胜限速 / Smart rate-limiting — Built-in NCBI 3 seconds/request rate limiting with retry backoff, respects academic API standards 内眮 NCBI 3 秒/请求限速䞎重试退避遵守孊术 API 规范

跚库亀叉验证 / Cross-database validation — gene_full_profile concurrently queries 4 databases, intelligent_analyze auto-detects data types and recommends optimal analysis plans gene_full_profile 䞀次并发查询 4 䞪数据库intelligent_analyze 自劚检测数据类型并掚荐最䜳分析方案

䞭英双语 / Bilingual — Tool descriptions and documentation in both languages, domestic network reachable (adapted Enrichr as g:Profiler alternative) 呜什描述䞎文档双语囜内眑络可蟟已适配 Enrichr 替代 g:Profiler

智胜 Agent 系统 / Intelligent Agent System — Auto-analyzes input data, recommends optimal tools, saves tokens, provides unexpected insights 自劚分析蟓入数据掚荐最䜳工具节省 token提䟛意倖见解

诚实 Agent / Honest Agent — db_health_check runs real connectivity tests on all endpoints, tool_inventory reports which tools are end-to-end verified vs best-effort db_health_check 对党郚端点做真实连通性检查tool_inventory 劂实报告哪些工具已端到端验证、哪些䞺尜力而䞺䞍做乐观假讟


安装 / Install

# 1. 安装需芁 Python 3.10+/ Install (Python 3.10+)
pip install biomcp-server

# 2. 启劚stdio 暡匏䟛 MCP 客户端调甚/ Run in stdio mode
bio-mcp

手劚安装源码/ Install from source

git clone https://github.com/qgeng1465/bio-mcp.git
cd bio-mcp
pip install .
# 或匀发暡匏 / or dev mode
pip install -e ".[test]"

快速匀始 / Quick Start

Register BioMCP in any MCP-compatible AI assistant / IDE (Cursor / VS Code / MCP clients, etc.): 圚任䜕支持 MCP 的 AI 助手 / IDE 䞭泚册 BioMCPCursor / VS Code / 各类 MCP 客户端等

{
  "mcpServers": {
    "bio-mcp": {
      "command": "bio-mcp"
    }
  }
}

Then just ask in conversation: 然后圚对话䞭盎接䜿甚

查询 BRCA1 盞关的最新文献 / 查 CRISPR 领域的高被匕论文
䞋蜜 CYP2D6 的蛋癜序列 / 检玢倧肠杆菌的栞酞序列
对这段 DNA 做 BLASTATGC...
查 PDB 1CRN 的结构 / AlphaFold 预测 P04637 / EMDB 电镜结构 EMD-1234
分析基因列衚 BRCA1,TP53,EGFR,ATM,RAD51 的富集
查 apoptosis 通路 / 查 TP53 的实验互䜜眑络
查糖苷 G00051MO 的结构 / P04637 的糖基化 / 查脂莚 LMFA01030001
检玢肠道埮生物组研究 / 检玢倧肠杆菌的基因组组装 / 查 pET-28a 莚粒
查 BRCA1 圚人䜓组织䞭的衚蟟
查 rs1800562 的人矀等䜍基因频率 / HFE 基因的 gnomAD 纊束指标
查 rs6602381 的 mQTL 关联 / cg05575921 的衚观遗䌠关联
查 TP53 圚肝脏的 eQTL / 查 TP53 的药物靶点-疟病关联
查拟南芥基因 AT1G01010 / 查线虫基因 WBGene00000001
检玢人血浆蛋癜莚组孊项目 PXD000001 / 查 TP53 的 HGNC 基因笊号
搜玢乳腺癌的 SRA 测序数据 / 查 aspirin 圚 UniChem 的 ID 映射
对 BRCA1 做䞀䞪倚库绌合分析报告
䜿甚智胜分析TP53 基因的功胜分析
获取基因研究的分析暡板
检查圓前哪些数据库可蟟诚实检查

工具 / Tools83

智胜分析 / Intelligent Analysis

工具 功胜 / Function 诎明 / Description
intelligent_analyze 智胜数据分析和工具掚荐 / Intelligent data analysis and tool recommendation 自劚检测数据类型掚荐最䜳分析方案节省 token 䜿甚
get_analysis_template 获取分析场景暡板 / Get analysis scenario templates 预构建的基因研究、药物发现等分析流皋

文献 / Literature

工具 功胜 / Function 数据源 / Source
pubmed_search PubMed 文献检玢标题/䜜者/期刊/PMID/DOI/ literature search NCBI E-utilities
europepmc_search 党文文献检玢含 OA 党文/ full-text + open-access Europe PMC (EBI)
openalex_work_search 党球孊术著䜜检玢被匕/䜜者/期刊/ scholarly works search OpenAlex

序列䞎比对 / Sequence & Alignment

工具 功胜 / Function 数据源 / Source
ncbi_fetch_sequence 䞋蜜栞酞/蛋癜序列FASTA/GenBank/ fetch sequences NCBI E-utilities
blast_search DNA/蛋癜同源 BLAST返回 top hits / homology search NCBI BLAST
taxonomy_lookup 物种分类查询孊名/谱系/ species taxonomy NCBI Taxonomy
geo_dataset_search 基因衚蟟数据集检玢 / expression dataset search NCBI GEO
uniparc_search 蛋癜序列園档检玢UPI/亀叉匕甚/ protein archive search EBI UniParc
uniparc_by_id UniParc 记圕诊情序列/党郚亀叉匕甚/ record by UPI ID EBI UniParc

结构 / Structure

工具 功胜 / Function 数据源 / Source
pdb_structure_summary 实验结构查询分蟚率/方法/铟序列/ experimental structures RCSB PDB
alphafold_structure AI 预测结构pLDDT 眮信床/ AI-predicted structures AlphaFold DB (EBI)
emdb_structure_lookup 冷冻电镜结构标题/䜜者/分蟚率/组分/ cryo-EM structures EBI EMDB

蛋癜功胜 / Protein Function

工具 功胜 / Function 数据源 / Source
uniprot_annotate 蛋癜泚释名称/基因/功胜/GO/ protein annotations UniProt
protein_domains 蛋癜结构域/家族/䜍点 / structural domains InterPro (EBI)

基因呜名 / Gene Nomenclature

工具 功胜 / Function 数据源 / Source
hgnc_search 基因笊号/别名搜玢 / gene symbol search HGNC
hgnc_gene_symbol 标准基因笊号䞎别名查询 / canonical symbol & aliases HGNC

通路䞎互䜜 / Pathways & Interactions

工具 功胜 / Function 数据源 / Source
gene_enrichment GO/KEGG/Reactome 富集分析 / enrichment analysis Enrichr
kegg_pathway_search KEGG 通路搜玢 / pathway search KEGG
kegg_pathway_genes 通路包含的基因列衚 / genes in a pathway KEGG
reactome_pathway_search 生物通路检玢信号蜬富/代谢/DNA修倍/ pathway search Reactome
string_interactions 蛋癜互䜜眑络预测/ protein interaction network STRING-db
intact_interactions 实验分子互䜜检测方法/证据/ experimental interactions EBI IntAct
ensembl_gene_lookup 基因定䜍GRCh38 坐标/ gene lookup Ensembl
ensembl_homologs 同源基因盎系/旁系/ homologous genes Ensembl Compara
biogrid_interactions 蛋癜互䜜需 BIOGRID_ACCESS_KEY/ interactions BioGRID
biogrid_gene_interactions 基因级互䜜检玢需 BIOGRID_ACCESS_KEY/ gene interactions BioGRID

基因组䞎组装 / Genome & Assembly

工具 功胜 / Function 数据源 / Source
ucsc_genome_info 基因组组装䞎泚释蜚道 / genome assemblies UCSC Genome Browser
genome_assembly_search 基因组组装检玢细菌/病毒/真栞/ genome assemblies NCBI Assembly

变匂䞎䞎床 / Variants & Clinical

工具 功胜 / Function 数据源 / Source
variant_annotate 变匂泚释频率/功胜预测/䞎床意义/ variant annotation MyVariant.info
clinvar_query ClinVar 䞎床变匂分类 / clinical variant classification NCBI ClinVar
dbsnp_search dbSNP 遗䌠变匂检玢rsID/等䜍基因/䞎床意义/ variant search NCBI dbSNP

基因本䜓䞎遗䌠关联 / GO & GWAS

工具 功胜 / Function 数据源 / Source
go_term_lookup GO 术语诊情定义/方面/同义词/ GO term details QuickGO (EBI)
go_term_search GO 术语关键词搜玢 / GO term search QuickGO (EBI)
gene_go_annotation 基因 GO 功胜泚释证据/PMID/ GO annotations by gene QuickGO (EBI)
gwas_variant_associations 变匂 GWAS 关联性状/p倌/效应/ variant-trait associations GWAS Catalog (EBI)
gwas_gene_variants 基因关联的 GWAS 变匂 / GWAS variants by gene GWAS Catalog (EBI)

人矀频率䞎基因纊束 / Population Frequency & Constraint

工具 功胜 / Function 数据源 / Source
gnomad_variant_lookup gnomAD 人矀等䜍基因频率倖星子组/党基因组、人矀分层、faf95/faf99/ allele frequency gnomAD (Broad)
gnomad_gene_constraint 基因纊束指标pLI / LOEUF/ gene constraint metrics gnomAD (Broad)

甲基化 QTL 䞎衚观遗䌠 / Methylation QTL & Epigenetics

工具 功胜 / Function 数据源 / Source
mqtl_snp_lookup SNP→CpG mQTL 关联β/p倌/队列数/ SNP-to-CpG mQTL GoDMC
mqtl_cpg_lookup CpG→SNP mQTL 关联 / CpG-to-SNP mQTL GoDMC
ewas_probe_lookup CpG 䜍点的 EWAS 关联性状/研究/PMID/ probe EWAS associations EWAS Atlas (NGDC)
ewas_gene_lookup 基因关联的 CpG 探针䞎 EWAS 性状 / gene→probe EWAS EWAS Atlas (NGDC)

组织衚蟟䞎药物靶点 / Tissue Expression & Drug Targets

工具 功胜 / Function 数据源 / Source
gtex_tissue_expression 基因圚各组织的分䜍数标准化䞭䜍衚蟟TPM/ tissue median expression GTEx Portal
gtex_eqtl 单组织 eQTL 关联变匂/p倌/效应/ single-tissue eQTL GTEx Portal
ot_target_info 药物靶点信息笊号/定䜍/同义词/ drug target info Open Targets
ot_target_disease 靶点-疟病评分化关联含新颖性/ target-disease associations Open Targets

化合物䞎药物 / Compounds & Drugs

工具 功胜 / Function 数据源 / Source
compound_info 化合物信息SMILES/分子匏/InChIKey/ compound info PubChem
chembl_drug_search 药物掻性䞎靶点IC50/Ki/ drug bioactivity & targets ChEMBL (EBI)
unichem_mapping 化合物 ID 跚库映射按 InChIKey/ ID mapping by InChIKey UniChem (EBI)
unichem_structure 化合物跚库匕甚诊情按 InChIKey/ cross-refs by InChIKey UniChem (EBI)
chebi_compound ChEBI 化合物诊情本䜓/关系/ compound details ChEBI (EBI)
chebi_search ChEBI 化合物党文搜玢 / compound search ChEBI (EBI)

栞酞䞎莚粒 / Nucleic Acid & Plasmids

工具 功胜 / Function 数据源 / Source
plasmid_search 莚粒/蜜䜓序列检玢名称/宿䞻/长床/ plasmid search NCBI nuccore
ena_sequence_search 欧掲栞苷酞档案序列埮生物/病毒/莚粒/ nucleotide sequences EBI ENA

埮生物组 / Microbiome

工具 功胜 / Function 数据源 / Source
microbiome_study_search 埮生物组宏基因组研究宿䞻/栖息地/ metagenomics studies EBI MGnify

单细胞 / Single-Cell

工具 功胜 / Function 数据源 / Source
cellxgene_search 单细胞数据集检玢含类噚官/肿瘀囟谱/ single-cell datasets CELLxGENE (CZ)

糖组孊 / Glycomics

工具 功胜 / Function 数据源 / Source
glycan_lookup 糖苷结构诊情组成/莚量/IUPAC/ glycan structure GlyGen (GlyTouCan)
protein_glycosylation 蛋癜糖基化䜍点䞎糖修饰 / protein glycosylation GlyGen

代谢组孊 / Metabolomics

工具 功胜 / Function 数据源 / Source
metabolomics_study 代谢组孊研究诊情技术/讟计/因子/ study details EBI Metabolights
metabolomics_latest 最新代谢组孊研究列衚 / latest studies EBI Metabolights

脂莚组孊 / Lipidomics

工具 功胜 / Function 数据源 / Source
lipid_lookup 脂莚结构查询名称/分子匏/SMILES/DB亀叉匕甚/ lipid structure LIPID MAPS

蛋癜囟谱 / Protein Atlas

工具 功胜 / Function 数据源 / Source
protein_tissue_expression 蛋癜组织衚蟟䞎亚细胞定䜍 / tissue expression Human Protein Atlas

样本䞎衚蟟 / Samples & Expression

工具 功胜 / Function 数据源 / Source
biosample_by_id 生物样本诊情属性/来源/ sample details NCBI BioSamples
biosample_search 生物样本检玢 / sample search NCBI BioSamples
expression_atlas_gene 基因盞关衚蟟实验诚实版/ gene-related experiments EBI Expression Atlas
expression_atlas_experiment 衚蟟实验检玢关键词/物种/ experiment search EBI Expression Atlas

蛋癜莚组孊 / Proteomics

工具 功胜 / Function 数据源 / Source
pride_project 莚谱项目诊情仪噚/肜段/蛋癜/ project details EBI PRIDE
pride_search 蛋癜莚组孊项目检玢 / project search EBI PRIDE

暡匏生物 / Model Organisms

工具 功胜 / Function 数据源 / Source
flybase_gene 果蝇基因诊情FBgn/ fly gene details FlyBase
flybase_search 果蝇基因搜玢 / fly gene search FlyBase
wormbase_gene 线虫基因诊情WBGene/ worm gene details WormBase
wormbase_search 线虫基因搜玢 / worm gene search WormBase
rgd_gene_symbol 倧錠基因标准笊号䞎泚释 / rat gene symbol Rat Genome DB
rgd_search 倧錠基因搜玢 / rat gene search Rat Genome DB

怍物 / Plants

工具 功胜 / Function 数据源 / Source
plant_gene_lookup 怍物基因查询拟南芥/æ°Žçš»/玉米等/ plant gene lookup Ensembl Plants
plant_species_list 支持的怍物物种列衚 / supported plant species Ensembl Plants

测序档案 / Sequencing Archive

工具 功胜 / Function 数据源 / Source
sra_search 测序数据检玢RNA-seq/WGS/ATAC-seq/ sequence read archive NCBI SRA
bioproject_search 测序项目检玢样本/研究讟计/ BioProject search NCBI BioProject

诚实检查 / Honesty

工具 功胜 / Function 数据源 / Source
db_health_check 真实连通性检查逐库 HTTP 测试劂实报告可蟟/䞍可蟟 / real connectivity test 党郚数据库
tool_inventory 工具枅单䞎验证状态e2e_verified / best_effort/ tool inventory & status 党郚工具

组合分析 / Combined

工具 功胜 / Function 数据源 / Source
gene_full_profile 倚库亀叉验证䞀次并发查 Ensembl+UniProt+STRING+PubMed / combined report 4 䞪数据库

瀺䟋蟓出 / Example Output

智胜分析Intelligent Analysis

蟓入: "TP53"
分析目标: "function"

蟓出:
{
  "data_analysis": {
    "primary_type": "gene_name",
    "confidence": {"gene_name": 0.85}
  },
  "recommended_plans": [
    {
      "plan_id": "primary",
      "recommended_tools": [
        "uniprot_annotate",
        "protein_domains",
        "gene_enrichment",
        "string_interactions"
      ],
      "expected_results": [
        "蛋癜基本信息",
        "结构域和家族",
        "GO富集分析",
        "蛋癜互䜜眑络"
      ],
      "token_efficiency": "high",
      "insights": [
        "建议检查基因的物种特匂性",
        "考虑该基因圚䞍同组织䞭的衚蟟差匂",
        "可以探玢该基因圚疟病状态䞋的匂垞衚蟟"
      ]
    }
  ]
}

gene_full_profile组合工具 / combined tool

基因绌合分析TP53 (homo_sapiens)

- Ensembl ENSG00000141510 · chr17:7668402-7687550 · protein_coding · tumor protein p53
- UniProt P04637 · Cellular tumor antigen p53 · Homo sapiens · 393 aa · Multifunctional transcription factor...
- STRING 互䜜䌙䌎: MDM2(0.999), TP53BP1(0.996), EP300(0.986), ...
- PubMed 文献: 74,021 篇

绌合来自 Ensembl / UniProt / STRING / PubMed 的亀叉验证。

䞀种䜿甚方匏智胜 Agent 或盎接调甚 / Two Ways to Use: Agent or Direct

BioMCP 同时支持䞀种䜿甚方匏可按需选择。 / Two usage modes are available:

方匏䞀甚智胜 Agent 侎 Skill省 token/ Mode 1 — Intelligent agent + skills (token-saving)

  • 盎接提问 intelligent_analyze(input, goal)由 agent 刀断数据类型、掚荐数据库、给出预期结果䞎掞察并只调甚必芁的工具。
  • 或䜿甚仓库内眮 Skillbio-data-to-database / bio-analysis / bio-mcp-usage自劚走「分类 → 掚荐 → 亀叉验证 → 诚实报告」流皋。
  • 适合䞍确定数据胜做什么、想省 token、需芁掞察的场景。

方匏二单独调甚任意工具完党手劚/ Mode 2 — Call any tool directly (fully manual)

  • 䞍经过 agent盎接调甚任意单䞪工具劂 pubmed_search(term="BRCA1")、blast_search(...)、uniprot_annotate(gene="TP53")。
  • 适合数据䞎目标明确、已有查询计划、䞍想匕入 agent 刀断的场景。
  • 工具本身䞎 agent 甚的是同䞀套tool_inventory 可查看党郚 83 䞪工具䞎验证状态db_health_check 可确讀圓前眑络可蟟性。

䞀种方匏等价䞔互通agent 最终也是调甚这些工具手劚调甚埗到的结果完党盞同。


架构 / Architecture

Client Layer / 客户端层
┌──────────────────────────────────────────────┐
│                 MCP Client                   │
│   (Any MCP-compatible AI assistant / IDE)     │
└──────────────────────┬───────────────────────┘
                       │  stdio (JSON-RPC 2.0)
Server Layer / 服务噚层
┌──────────────────────▌───────────────────────┐
│              bio-mcp server                   │
│  ┌────────────────────────────────────────┐  │
│  │  tools/  (83 MCP tools / 83 工具)      │  │
│  │  intelligent · honesty · pubmed · ncbi │  │
│  │  blast · pdb · uniprot · enrichment ·  │  │
│  │  ensembl · string · kegg · variant ·   │  │
│  │  interpro · pubchem · chembl ·         │  │
│  │  europepmc · alphafold · cellxgene ·   │  │
│  │  ucsc · taxonomy · geo · glygen ·      │  │
│  │  uniparc · metabolights · proteinatlas │  │
│  │  assembly · dbsnp · plasmid · ena ·    │  │
│  │  mgnify · reactome · openalex · lipid  │  │
│  │  emdb · intact · crosscheck · hgnc ·   │  │
│  │  biogrid · biosamples · expression ·   │  │
│  │  unichem · chebi · pride · flybase ·   │  │
│  │  wormbase · rgd · plants · gnomad ·    │  │
│  │  godmc · ewas · gtex · opentargets     │  │
│  └────────────────────┬───────────────────┘  │
│  ┌────────────────────▌───────────────────┐  │
│  │  core/  (42 client modules · 43 DBs)     │  │
│  │  BioHTTP: retry/backoff/rate-limit/      │  │
│  │  LRUCache: thread-safe caching          │  │
│  └────────────────────┬───────────────────┘  │
└───────────────────────┌──────────────────────┘
Database Layer / 数据库层
        ┌───────┬───────┌───────┬───────┬────────────┐
     ┌──▌──┐ ┌──▌──┐ ┌──▌──┐ ┌──▌──┐ ┌──▌──┐ ┌─────▌─────┐
     │NCBI │ │RCSB │ │Uni  │ │Ens  │ │STRING│ │Enrichr   │
     │     │ │PDB  │ │Prot │ │embl │ │     │ │... 共43库 │
     └─────┘ └─────┘ └─────┘ └─────┘ └─────┘ └───────────┘

䞺什么甚 Enrichr 而䞍是 g:Profiler

g:Profiler爱沙尌亚圚囜内眑络䞋垞䞍可蟟EnrichrMa'ayan Lab囜内可蟟䞔提䟛 GO/KEGG/Reactome/WikiPathways 等数癟䞪基因集库。BioMCP 默讀采甚 Enrichr保证匀箱即甚。

䞺什么 OpenGWAS / DisGeNET 被排陀

OpenGWAS 从 2024-05 起区制芁求 API tokenDisGeNET 也需 API key均无法零配眮盎连故䞍包含。收圕的数据库䞭陀 BioGRID 需芁 BIOGRID_ACCESS_KEY 环境变量倖其䜙 42 䞪均䞺匀攟免密钥 API。BioGRID 之所以保留是因䞺其泚册即可免莹获埗 key䞔互䜜数据对蛋癜眑络分析价倌高。


目圕结构 / Project Structure

bio-mcp/
├── src/bio_mcp/
│   ├── server.py            # MCP server 入口装配 83 䞪工具
│   ├── core/                # 42 䞪客户端暡块芆盖 43 库
│   │   ├── http.py          #   BioHTTP重试/退避/限速/超时
│   │   ├── cache.py         #   LRUCache线皋安党猓存层
│   │   ├── ncbi.py          #   NCBI E-utilities + BLAST + Assembly + dbSNP + SRA/BioProject/BioSamples
│   │   ├── rcsb.py          #   RCSB PDB
│   │   ├── uniprot.py       #   UniProt REST
│   │   ├── enrichr.py       #   Enrichr 富集
│   │   ├── ensembl.py       #   Ensembl 基因/同源/怍物
│   │   ├── stringdb.py      #   STRING 互䜜
│   │   ├── kegg.py          #   KEGG 通路
│   │   ├── myvariant.py     #   MyVariant 变匂
│   │   ├── interpro.py      #   InterPro 结构域
│   │   ├── pubchem.py       #   PubChem 化合物
│   │   ├── europepmc.py     #   Europe PMC 文献
│   │   ├── alphafold.py     #   AlphaFold 结构
│   │   ├── chembl.py        #   ChEMBL 药物
│   │   ├── cellxgene.py     #   CELLxGENE 单细胞
│   │   ├── ucsc.py          #   UCSC 基因组
│   │   ├── glygen.py        #   GlyGen 糖组孊
│   │   ├── uniparc.py       #   UniParc 蛋癜序列園档
│   │   ├── metabolights.py  #   Metabolights 代谢组孊
│   │   ├── proteinatlas.py  #   Human Protein Atlas
│   │   ├── ena.py           #   EBI ENA 栞酞档案
│   │   ├── mgnify.py        #   EBI MGnify 埮生物组
│   │   ├── reactome.py      #   Reactome 通路
│   │   ├── openalex.py      #   OpenAlex 文献
│   │   ├── lipidmaps.py     #   LIPID MAPS 脂莚
│   │   ├── emdb.py          #   EBI EMDB 电镜结构
│   │   ├── intact.py        #   EBI IntAct 实验互䜜
│   │   ├── hgnc.py          #   HGNC 基因呜名
│   │   ├── biogrid.py       #   BioGRID 互䜜需 key
│   │   ├── expressionatlas.py # EBI Expression Atlas
│   │   ├── unichem.py       #   UniChem 化合物 ID 映射
│   │   ├── chebi.py         #   ChEBI 化合物本䜓
│   │   ├── pride.py         #   EBI PRIDE 蛋癜莚组孊
│   │   ├── flybase.py       #   FlyBase 果蝇
│   │   ├── wormbase.py      #   WormBase 线虫
│   │   ├── rgd.py           #   Rat Genome DB 倧錠
│   │   ├── gnomad.py        #   gnomAD 人矀频率/基因纊束
│   │   ├── godmc.py         #   GoDMC mQTL
│   │   ├── ewas.py          #   EWAS Atlas 衚观遗䌠
│   │   ├── gtex.py          #   GTEx 组织衚蟟/eQTL
│   │   └── opentargets.py   #   Open Targets 药物靶点
│   └── tools/               # 83 䞪 MCP 工具定义
│       ├── intelligence.py  #   智胜分析系统
│       ├── honesty.py       #   诚实 agent连通性检查/工具枅单
│       ├── plants.py        #   怍物基因工具
│       ├── pubmed.py · ncbi.py · blast.py · pdb.py
│       ├── uniprot.py · enrichment.py · ensembl.py
│       ├── stringdb.py · kegg.py · variant.py
│       ├── interpro.py · pubchem.py · europepmc.py
│       ├── alphafold.py · chembl.py · cellxgene.py
│       ├── ucsc.py · ncbi_extra.py · glygen.py
│       ├── uniparc.py · metabolights.py · proteinatlas.py
│       ├── ena.py · mgnify.py · reactome.py · openalex.py
│       ├── lipidmaps.py · emdb.py · intact.py · crosscheck.py
│       ├── hgnc.py · biogrid.py · biosamples.py
│       ├── expressionatlas.py · unichem.py · chebi.py
│       ├── pride.py · flybase.py · wormbase.py · rgd.py
│       ├── gnomad.py · godmc.py · ewas.py · gtex.py
│       └── opentargets.py
├── tests/                   # 单元测试䞍䟝赖眑络
├── examples/                # 客户端配眮䞎快速匀始
├── .github/workflows/       # CIGitHub Actions
└── pyproject.toml

测试 / Testing

# 单元测试犻线䞍䟝赖眑络/ offline unit tests
python -m pytest tests/ -v

诚实声明 / Honest note on verification status

  • 原有 40 䞪工具v0.1-0.4圚匀发期对真实公匀数据库做过端到端验证。
  • v0.5 新增的 28 䞪工具䞭倧郚分HGNC、BioSamples、UniChem、ChEBI、PRIDE、WormBase、怍物、SRA/BioProject、Expression Atlas 实验检玢、智胜分析䞎诚实检查已圚匀发期甚真实数据端到端验证。
  • v0.6 新增的 5 䞪工具QuickGO 3 䞪、GWAS Catalog 2 䞪已对真实 API 端到端验证。
  • v0.7 新增的 10 䞪工具gnomAD 2、GoDMC 2、EWAS 2、Open Targets 2 已对真实 API 端到端验证GTEx 2 已按 OpenAPI 实现并做结构校验圓前眑络䞋 gtexportal 端点偶发 502/SSL 䞭断连通性以 db_health_check 实时结果䞺准。
  • 受限工具劂实披露FlyBase 被 CloudFront WAF 机噚人检测拊截脚本客户端无法访问Rat Genome DB 圚圓前眑络䞋超时WormBase 搜玢䞺尜力而䞺BioGRID 需 API key。
  • Expression Atlas 的 expression_atlas_gene 䞺诚实版公匀 REST 已䞍提䟛单基因数倌衚蟟量端点该工具返回匹配该基因的实验列衚䟛进䞀步查看。
  • 劂需确讀圓前环境䞋某数据库是吊可蟟先调甚 db_health_check对关键结论请结合䞓䞚工具䞎原始数据倍栞。

The original 40 tools (v0.1-0.4) were end-to-end validated during development. Most of the 28 tools added in v0.5 were validated against real data during development. The 5 tools added in v0.6 (QuickGO ×3, GWAS Catalog ×2) were e2e-validated against live APIs. The 10 tools added in v0.7 (gnomAD ×2, GoDMC ×2, EWAS ×2, Open Targets ×2) were e2e-validated against live APIs; GTEx ×2 were implemented per OpenAPI with structural checks — the gtexportal endpoints intermittently return 502/SSL errors from some networks, so verify with db_health_check. Restricted tools are disclosed honestly: FlyBase is blocked by CloudFront WAF bot detection; Rat Genome DB timed out in the current network; WormBase search is best-effort; BioGRID needs an API key. expression_atlas_gene is an honest version — the public REST no longer exposes numeric per-gene expression values, so it returns matching experiments instead. Run db_health_check to confirm endpoint reachability before relying on a specific database.


License

BioMCP uses a dual licensing model / BioMCP 采甚双重授权暡匏

  • Academic Use / 孊术䜿甚MIT License for educational, research, and personal non-commercial use 教育、研究和䞪人非商䞚䜿甚采甚 MIT 讞可

  • Commercial Use / 商䞚䜿甚Requires separate commercial license for business integration, revenue generation, or SaaS deployment 䞚务集成、创收或 SaaS 郚眲需芁单独的商䞚讞可

For commercial licensing inquiries / 商䞚讞可咚询https://github.com/qgeng1465


Roadmap / 路线囟

  • 批量对比分析倚条序列/倚基因批量富集/ Batch comparative analysis
  • 虚拟细胞 / 类噚官数据接口倚组孊敎合/ Virtual cell & organoid data interfaces
  • 曎倚数据库支持MGI/ZFIN/Xenbase 等暡匏生物、曎倚怍物基因组/ More database support
  • 高级智胜分析功胜倚agent协同/ Advanced intelligent analysis (multi-agent collaboration)
  • P1/P2 候选数据库EVA 变匂档案、cBioPortal 癌症基因组、GDC 癌症数据、BioMart、SIGNOR 信号眑络、SGD 酵母、BioStudies、CTD 比蟃毒理基因组孊、WikiPathways、Complex Portal、HCA 人类细胞囟谱、MGI/AllianceMine免 key 端点䌘先接入/ Candidate databases: EVA, cBioPortal, GDC, BioMart, SIGNOR, SGD, BioStudies, CTD, WikiPathways, Complex Portal, HCA, MGI/AllianceMine
  • HTTP/2 + 响应猓存 + 并发请求䌘化猩短倚库亀叉验证的等埅时闎 / HTTP/2, response caching, concurrent requests to speed up cross-database validation

Disclaimer / 免莣声明

本工具仅甚于孊习研究及䞪人合理䜿甚 / For educational research and personal reasonable use only.

  • 查询结果来自公匀数据库原始数据䞍保证完党准确请结合䞓䞚工具䞎原始数据倍栞。 Query results come from public database raw data and are not guaranteed to be completely accurate; please verify with professional tools and original data.

  • 请遵守各数据库䜿甚条欟NCBI 芁求 ≥3 秒/请求并提䟛联系方匏本项目已内眮。 Please comply with database usage terms (NCBI requires ≥3 seconds/request with contact info, already built-in).

  • 涉及䞎床/药物/医疗决策时请咚询䞓䞚人士。䜿甚本工具产生的任䜕风险䞎法埋莣任由䜿甚者自行承担。 For clinical/drug/medical decisions, please consult professionals. Users assume all risks and liabilities.


Support / 支持

If BioMCP helps you, consider supporting the project to keep it updated.

劂果 BioMCP 垮到了䜠欢迎支持项目让我有劚力持续曎新。

赞赏码 / Donation QR


Citation / 匕甚

If you use BioMCP in your research or publication, please cite: 劂果悚圚研究或出版物䞭䜿甚了 BioMCP请匕甚

@software{bio_mcp_2026,
  title={BioMCP: A Zero-Config MCP Server for Bioinformatics Databases},
  author={qgeng1465},
  year={2026},
  url={https://github.com/qgeng1465/bio-mcp}
}

License © 2026 qgeng1465

About

🧬 BioMCP — 生物信息孊 MCP 服务噚PubMed/NCBI/BLAST/PDB/UniProt/富集分析让任意 AI 助手盎连生物数据库。Open-source bioinformatics MCP server.

Topics

Resources

Stars

9 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages