BioMCP
BioMCP is an MCP server that connects AI assistants to 43 open bioinformatics databases via 83 zero-config tools for biomedical research.
Search literature: PubMed, Europe PMC, OpenAlex
Fetch nucleotide/protein sequences from NCBI, ENA, UniParc; run BLAST homology searches
Retrieve structures: PDB, AlphaFold, EMDB
Annotate proteins and domains: UniProt, InterPro, HGNC gene symbols, GO terms
Explore pathways and interactions: KEGG, Reactome, STRING, IntAct, BioGRID, Ensembl homologs
Analyze variants: MyVariant, ClinVar, dbSNP, gnomAD, GWAS Catalog
Look up methylation/QTL data: GoDMC mQTL, EWAS Atlas, GTEx eQTL/tissue expression
Query drugs and compounds: PubChem, ChEMBL, UniChem, ChEBI, LIPID MAPS, Open Targets
Find datasets across omics: GEO, SRA, BioProject, BioSamples, Expression Atlas, PRIDE, Metabolights, MGnify, CELLxGENE
Access model organisms and plants: FlyBase, WormBase, RGD, Ensembl Plants
Run combined analyses: gene_full_profile, intelligent_analyze, analysis templates
Verify reliability: db_health_check and tool_inventory report real reachability and verification status
Provides PubMed literature search capabilities, enabling retrieval of biomedical papers by title, author, journal, PMID, or DOI, and integration into combined gene analysis reports.
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., "@BioMCP Look up recent publications on CRISPR-Cas9"
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.
BioMCP — Bioinformatics MCP Server
English | 汉语
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.
Features
Standard MCP protocol — Based on official MCP SDK with stdio transport, compatible with all MCP clients
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
Zero-config — pip install biomcp-server one command, no database setup, no API keys required
Authoritative public data — All from official APIs: NCBI / RCSB / UniProt / Ensembl / EBI / STRING / KEGG / GlyGen / Reactome / OpenAlex, etc.
Smart rate-limiting — Built-in NCBI 3 seconds/request rate limiting with retry backoff, respects academic API standards
Cross-database validation — gene_full_profile concurrently queries 4 databases, intelligent_analyze auto-detects data types and recommends optimal analysis plans
Bilingual — Tool descriptions are available in both English and Chinese, and the default endpoints are reachable from mainland China (Enrichr is used in place of g:Profiler)
Intelligent Agent System — Auto-analyzes input data, recommends optimal tools, saves tokens, provides unexpected insights
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
Related MCP server: BioContextAI Knowledgebase MCP
Install
# Install (Python 3.10+)
pip install biomcp-server
# Run in stdio mode
bio-mcpInstall from source
git clone https://github.com/qgeng1465/bio-mcp.git
cd bio-mcp
pip install .
# or dev mode
pip install -e ".[test]"Quick Start
Register BioMCP in any MCP-compatible AI assistant / IDE (Cursor / VS Code / MCP clients, etc.):
{
"mcpServers": {
"bio-mcp": {
"command": "bio-mcp"
}
}
}Then just ask in conversation:
Search the latest literature on BRCA1 / highly cited papers on CRISPR
Download the protein sequence for CYP2D6 / fetch nucleotide sequences for E. coli
BLAST this DNA: ATGC...
Look up the structure of PDB 1CRN / AlphaFold prediction for P04637 / EMDB cryo-EM structure EMD-1234
Run enrichment analysis on the gene list BRCA1,TP53,EGFR,ATM,RAD51
Look up the apoptosis pathway / the experimental interaction network of TP53
Look up the structure of glycan G00051MO / glycosylation of P04637 / lipid LMFA01030001
Search gut microbiome studies / E. coli genome assemblies / the pET-28a plasmid
Look up BRCA1 expression across human tissues
Look up the population allele frequency of rs1800562 / gnomAD constraint metrics for HFE
Look up mQTL associations for rs6602381 / epigenetic associations for cg05575921
Look up the liver eQTL for TP53 / TP53 drug-target–disease associations
Look up the Arabidopsis gene AT1G01010 / the C. elegans gene WBGene00000001
Search the human plasma proteomics project PXD000001 / the HGNC symbol for TP53
Search SRA sequencing data for breast cancer / UniChem ID mapping for aspirin
Produce a multi-database combined analysis report for BRCA1
Use intelligent analysis: functional analysis of the TP53 gene
Get an analysis template for gene research
Check which databases are currently reachable (honesty check)Tools (83)
Intelligent Analysis
Tool | Function | Description |
| Intelligent data analysis and tool recommendation | Auto-detects the data type, recommends the best analysis plan, saves tokens |
| Get analysis scenario templates | Pre-built analysis pipelines for gene research, drug discovery, and more |
Literature
Tool | Function | Source |
| literature search | NCBI E-utilities |
| full-text + open-access | Europe PMC (EBI) |
| scholarly works search | OpenAlex |
Sequence & Alignment
Tool | Function | Source |
| fetch sequences | NCBI E-utilities |
| homology search | NCBI BLAST |
| species taxonomy | NCBI Taxonomy |
| expression dataset search | NCBI GEO |
| protein archive search | EBI UniParc |
| record by UPI ID | EBI UniParc |
Structure
Tool | Function | Source |
| experimental structures | RCSB PDB |
| AI-predicted structures | AlphaFold DB (EBI) |
| cryo-EM structures | EBI EMDB |
Protein Function
Tool | Function | Source |
| protein annotations | UniProt |
| structural domains | InterPro (EBI) |
Gene Nomenclature
Tool | Function | Source |
| gene symbol search | HGNC |
| canonical symbol & aliases | HGNC |
Pathways & Interactions
Tool | Function | Source |
| enrichment analysis | Enrichr |
| pathway search | KEGG |
| genes in a pathway | KEGG |
| pathway search | Reactome |
| protein interaction network | STRING-db |
| experimental interactions | EBI IntAct |
| gene lookup | Ensembl |
| homologous genes | Ensembl Compara |
| interactions | BioGRID |
| gene interactions | BioGRID |
Genome & Assembly
Tool | Function | Source |
| genome assemblies | UCSC Genome Browser |
| genome assemblies | NCBI Assembly |
Variants & Clinical
Tool | Function | Source |
| variant annotation | MyVariant.info |
| clinical variant classification | NCBI ClinVar |
| variant search | NCBI dbSNP |
GO & GWAS
Tool | Function | Source |
| GO term details | QuickGO (EBI) |
| GO term search | QuickGO (EBI) |
| GO annotations by gene | QuickGO (EBI) |
| variant-trait associations | GWAS Catalog (EBI) |
| GWAS variants by gene | GWAS Catalog (EBI) |
Population Frequency & Constraint
Tool | Function | Source |
| allele frequency | gnomAD (Broad) |
| LOEUF)/ gene constraint metrics | gnomAD (Broad) |
Methylation QTL & Epigenetics
Tool | Function | Source |
| SNP-to-CpG mQTL | GoDMC |
| CpG-to-SNP mQTL | GoDMC |
| probe EWAS associations | EWAS Atlas (NGDC) |
| gene→probe EWAS | EWAS Atlas (NGDC) |
Tissue Expression & Drug Targets
Tool | Function | Source |
| tissue median expression | GTEx Portal |
| single-tissue eQTL | GTEx Portal |
| drug target info | Open Targets |
| target-disease associations | Open Targets |
Compounds & Drugs
Tool | Function | Source |
| compound info | PubChem |
| drug bioactivity & targets | ChEMBL (EBI) |
| ID mapping by InChIKey | UniChem (EBI) |
| cross-refs by InChIKey | UniChem (EBI) |
| compound details | ChEBI (EBI) |
| compound search | ChEBI (EBI) |
Nucleic Acid & Plasmids
Tool | Function | Source |
| plasmid search | NCBI nuccore |
| nucleotide sequences | EBI ENA |
Microbiome
Tool | Function | Source |
| metagenomics studies | EBI MGnify |
Single-Cell
Tool | Function | Source |
| single-cell datasets | CELLxGENE (CZ) |
Glycomics
Tool | Function | Source |
| glycan structure | GlyGen (GlyTouCan) |
| protein glycosylation | GlyGen |
Metabolomics
Tool | Function | Source |
| study details | EBI Metabolights |
| latest studies | EBI Metabolights |
Lipidomics
Tool | Function | Source |
| lipid structure | LIPID MAPS |
Protein Atlas
Tool | Function | Source |
| tissue expression | Human Protein Atlas |
Samples & Expression
Tool | Function | Source |
| sample details | NCBI BioSamples |
| sample search | NCBI BioSamples |
| gene-related experiments | EBI Expression Atlas |
| experiment search | EBI Expression Atlas |
Proteomics
Tool | Function | Source |
| project details | EBI PRIDE |
| project search | EBI PRIDE |
Model Organisms
Tool | Function | Source |
| fly gene details | FlyBase |
| fly gene search | FlyBase |
| worm gene details | WormBase |
| worm gene search | WormBase |
| rat gene symbol | Rat Genome DB |
| rat gene search | Rat Genome DB |
Plants
Tool | Function | Source |
| plant gene lookup | Ensembl Plants |
| supported plant species | Ensembl Plants |
Sequencing Archive
Tool | Function | Source |
| sequence read archive | NCBI SRA |
| BioProject search | NCBI BioProject |
Honesty
Tool | Function | Source |
| real connectivity test | All databases |
| best_effort)/ tool inventory & status | All tools |
Combined
Tool | Function | Source |
| combined report | 4 databases |
Example Output
Intelligent Analysis
Input: "TP53"
Goal: "function"
Output:
{
"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": [
"Basic protein information",
"Domains and families",
"GO enrichment analysis",
"Protein interaction network"
],
"token_efficiency": "high",
"insights": [
"Consider checking the species specificity of the gene",
"Consider how this gene's expression differs across tissues",
"You could explore aberrant expression of this gene in disease states"
]
}
]
}gene_full_profile (combined tool)
Combined analysis: 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 interaction partners: MDM2(0.999), TP53BP1(0.996), EP300(0.986), ...
- PubMed literature: 74,021 papers
Cross-validated across Ensembl / UniProt / STRING / PubMed.Two Ways to Use: Agent or Direct
Two usage modes are available:
Mode 1 — Intelligent agent + skills (token-saving)
Ask
intelligent_analyze(input, goal)directly: the agent classifies the data type, recommends databases, states the expected results and insights, and calls only the tools it needs.Or use one of the bundled skills (bio-data-to-database / bio-analysis / bio-mcp-usage), which follow the flow "classify → recommend → cross-validate → report honestly".
Best for: when you are not sure what the data can answer, want to save tokens, or need insights.
Mode 2 — Call any tool directly (fully manual)
Skip the agent and call any single tool, e.g.
pubmed_search(term="BRCA1"),blast_search(...),uniprot_annotate(gene="TP53").Best for: when the data and the goal are clear, you already have a query plan, or you don't want agent judgement in the loop.
The tools are the same ones the agent uses:
tool_inventorylists all 83 tools with their verification status, anddb_health_checkconfirms current reachability.
The two modes are equivalent and interchangeable: the agent ends up calling the same tools, and manual calls return exactly the same results.
Architecture
Client Layer
┌──────────────────────────────────────────────┐
│ MCP Client │
│ (Any MCP-compatible AI assistant / IDE) │
└──────────────────────┬───────────────────────┘
│ stdio (JSON-RPC 2.0)
Server Layer
┌──────────────────────▼───────────────────────┐
│ bio-mcp server │
│ ┌────────────────────────────────────────┐ │
│ │ tools/ (83 MCP tools) │ │
│ │ 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
┌───────┬───────┼───────┬───────┬────────────┐
┌──▼──┐ ┌──▼──┐ ┌──▼──┐ ┌──▼──┐ ┌──▼──┐ ┌─────▼─────┐
│NCBI │ │RCSB │ │Uni │ │Ens │ │STRING│ │Enrichr │
│ │ │PDB │ │Prot │ │embl │ │ │ │... 43 DBs │
└─────┘ └─────┘ └─────┘ └─────┘ └─────┘ └───────────┘Why Enrichr and not g:Profiler?
g:Profiler (Estonia) is frequently unreachable from mainland China; Enrichr (Ma'ayan Lab) is reachable there and provides hundreds of gene-set libraries including GO/KEGG/Reactome/WikiPathways. BioMCP uses Enrichr by default so it works out of the box.
Why OpenGWAS / DisGeNET are excluded
OpenGWAS has required an API token since 2024-05, and DisGeNET also needs an API key; neither can be used zero-config, so neither is included. Of the databases that are included, all 42 are open, keyless APIs except BioGRID, which needs a BIOGRID_ACCESS_KEY environment variable. BioGRID is kept because a key is free on registration and its interaction data is valuable for protein-network analysis.
Project Structure
bio-mcp/
├── src/bio_mcp/
│ ├── server.py # MCP server entry point (wires up the 83 tools)
│ ├── core/ # 42 client modules covering 43 databases
│ │ ├── http.py # BioHTTP: retry / backoff / rate-limit / timeout
│ │ ├── cache.py # LRUCache: thread-safe caching layer
│ │ ├── ncbi.py # NCBI E-utilities + BLAST + Assembly + dbSNP + SRA/BioProject/BioSamples
│ │ ├── rcsb.py # RCSB PDB
│ │ ├── uniprot.py # UniProt REST
│ │ ├── enrichr.py # Enrichr enrichment
│ │ ├── ensembl.py # Ensembl genes / homologs / plants
│ │ ├── stringdb.py # STRING interactions
│ │ ├── kegg.py # KEGG pathways
│ │ ├── myvariant.py # MyVariant variants
│ │ ├── interpro.py # InterPro domains
│ │ ├── pubchem.py # PubChem compounds
│ │ ├── europepmc.py # Europe PMC literature
│ │ ├── alphafold.py # AlphaFold structures
│ │ ├── chembl.py # ChEMBL drugs
│ │ ├── cellxgene.py # CELLxGENE single-cell
│ │ ├── ucsc.py # UCSC genomes
│ │ ├── glygen.py # GlyGen glycomics
│ │ ├── uniparc.py # UniParc protein sequence archive
│ │ ├── metabolights.py # Metabolights metabolomics
│ │ ├── proteinatlas.py # Human Protein Atlas
│ │ ├── ena.py # EBI ENA nucleotide archive
│ │ ├── mgnify.py # EBI MGnify microbiome
│ │ ├── reactome.py # Reactome pathways
│ │ ├── openalex.py # OpenAlex literature
│ │ ├── lipidmaps.py # LIPID MAPS lipids
│ │ ├── emdb.py # EBI EMDB cryo-EM structures
│ │ ├── intact.py # EBI IntAct experimental interactions
│ │ ├── hgnc.py # HGNC gene nomenclature
│ │ ├── biogrid.py # BioGRID interactions (API key required)
│ │ ├── expressionatlas.py # EBI Expression Atlas
│ │ ├── unichem.py # UniChem compound ID mapping
│ │ ├── chebi.py # ChEBI compound ontology
│ │ ├── pride.py # EBI PRIDE proteomics
│ │ ├── flybase.py # FlyBase Drosophila
│ │ ├── wormbase.py # WormBase C. elegans
│ │ ├── rgd.py # Rat Genome DB
│ │ ├── gnomad.py # gnomAD population frequency / gene constraint
│ │ ├── godmc.py # GoDMC mQTL
│ │ ├── ewas.py # EWAS Atlas epigenetics
│ │ ├── gtex.py # GTEx tissue expression / eQTL
│ │ └── opentargets.py # Open Targets drug targets
│ └── tools/ # 83 MCP tool definitions
│ ├── intelligence.py # intelligent analysis system
│ ├── honesty.py # honesty agent (connectivity check / tool inventory)
│ ├── plants.py # plant gene tools
│ ├── 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/ # unit tests (no network)
├── examples/ # client configs and quick start
├── .github/workflows/ # CI (GitHub Actions)
└── pyproject.tomlTesting
# offline unit tests
python -m pytest tests/ -vHonest note on verification status:**
The original 40 tools (v0.1-0.4) were end-to-end validated against real public databases during development. Most of the 28 tools added in v0.5 (HGNC, BioSamples, UniChem, ChEBI, PRIDE, WormBase, plants, SRA/BioProject, Expression Atlas experiment search, intelligent analysis and the honesty checks) were also validated end-to-end against real data. The 5 tools added in v0.6 (QuickGO ×3, GWAS Catalog ×2) were validated against live APIs. The 10 tools added in v0.7 (gnomAD ×2, GoDMC ×2, EWAS ×2, Open Targets ×2) were validated against live APIs; GTEx ×2 were implemented per the OpenAPI spec with structural checks — the gtexportal endpoints intermittently return 502/SSL errors, so treat
db_health_checkas the live answer. Restricted tools are disclosed honestly: FlyBase is blocked by CloudFront WAF bot detection; Rat Genome DB timed out on the current network; WormBase search is best-effort; BioGRID needs an API key.expression_atlas_geneis an honest version — the public REST API no longer exposes numeric per-gene expression values, so it returns matching experiments instead. Rundb_health_checkto confirm what is reachable before relying on a specific database.
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_geneis an honest version — the public REST no longer exposes numeric per-gene expression values, so it returns matching experiments instead. Rundb_health_checkto confirm endpoint reachability before relying on a specific database.
License
BioMCP uses a dual licensing model:
Academic Use: MIT License for educational, research, and personal non-commercial use
Commercial Use: Requires a separate commercial license for business integration, revenue generation, or SaaS deployment
For commercial licensing inquiries: https://github.com/qgeng1465
Roadmap
Batch comparative analysis Virtual cell & organoid data interfaces More database support Advanced intelligent analysis (multi-agent collaboration) Candidate databases: EVA, cBioPortal, GDC, BioMart, SIGNOR, SGD, BioStudies, CTD, WikiPathways, Complex Portal, HCA, MGI/AllianceMine HTTP/2, response caching, concurrent requests to speed up cross-database validation
Disclaimer
For educational research and personal reasonable use only.
Query results come from public database raw data and are not guaranteed to be completely accurate; please verify with professional tools and original data.
Please comply with database usage terms (NCBI requires ≥3 seconds/request with contact info, already built-in).
For clinical/drug/medical decisions, please consult professionals. Users assume all risks and liabilities.
Support
If BioMCP helps you, consider supporting the project to keep it updated.
Citation
If you use BioMCP in your research or publication, please cite:
@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
Available Tools
73 toolsalphafold_structureA
Query AlphaFold DB AI-predicted protein structures. 查询 AlphaFold DB 的 AI 蛋白结构预测:给定 UniProt accession,returns pLDDT confidence, sequence length, PDB download link. 返回 pLDDT 置信度、序列长度、3D 模型(PDB)下载链接。AlphaFold covers 200M+ proteins. AlphaFold 覆盖 2 亿+ 蛋白。
Inputs: uniprot_acc (required). Returns: result
biogrid_gene_interactionsA
Get protein interactions for a specific gene symbol from BioGRID. Input: gene symbol (TP53), optional organism ID (9606=human). Output: interaction partners with experimental evidence and detection methods.
Inputs: gene_symbol (required), organism. Returns: result
biogrid_interactionsB
Search protein interaction data from BioGRID database. Input: gene name or identifier (BRCA1, TP53). Output: protein-protein interactions with experimental evidence and publication references.
Inputs: search_name (required), search_type. Returns: result
bioproject_searchA
Search NCBI BioProject biological projects. 检索 NCBI BioProject 生物项目:按主题/项目编号(如 gut microbiome AND human、PRJNA123456),returns project accession/title/description/organism. 返回项目编号、标题、描述与物种,用于关联大规模测序项目与数据集。
Inputs: query (required), max_results. Returns: result
biosample_by_idA
Get biological sample metadata by sample ID. Input: sample ID (SAMN00000001, SAMEA123456). Output: sample accession, title, organism, status. 按样本ID获取生物样本元数据(通过 NCBI E-utilities)。
Inputs: sample_id (required). Returns: result
biosample_searchA
Search biological samples by keywords. Input: search term (human[Organism], cancer, tissue:lung). Output: list of matching samples with metadata. 按关键词搜索生物样本(通过 NCBI E-utilities)。
Inputs: term (required). Returns: result
blast_searchA
NCBI BLAST homology search for DNA or protein sequences. 对 DNA 或蛋白序列做 NCBI BLAST 同源搜索,返回 top hits(accession/物种/E值/一致性/描述)。For sequence identification, homolog discovery, primer validation. 用于鉴定未知序列、找同源基因、验证引物。
Inputs: sequence (required), program, database, max_hits. Returns: result
cellxgene_searchA
Search CELLxGENE (CZ) single-cell transcriptome datasets. 检索 CELLxGENE 单细胞转录组数据:按疾病/组织/关键词匹配已发布数据集(含类器官、肿瘤、免疫等单细胞图谱),for finding single-cell data. 用于单细胞研究找数据。
Inputs: query (required), max_results. Returns: result
chebi_compoundA
Query ChEBI compound by ChEBI ID. 按 ChEBI ID 查询化合物信息:输入 ChEBI 编号(如 CHEBI:15377 ATP),返回化合物名称、定义、化学属性与交叉引用,用于化学生物学研究。
Inputs: chebi_id (required). Returns: result
chebi_searchA
Search ChEBI compounds by name or keyword. 按化合物名称搜索 ChEBI:输入化合物名称或关键词(如 ATP/glucose),返回匹配的化合物列表,包含 ChEBI ID、名称与定义,用于化合物查询。
Inputs: name (required). Returns: result
chembl_drug_searchB
Query drug/compound bioactivity (ChEMBL, EBI). 查询药物/候选化合物:按名称返回 ChEMBL ID、SMILES、分子式、分子量、临床阶段与作用靶点及活性值(IC50/Ki),for medicinal chemistry & target research. 用于药物化学与靶点调研。
Inputs: name (required), include_targets. Returns: result
clinvar_queryA
Query ClinVar clinical variants (via NCBI E-utilities). 查询 ClinVar 临床变异:输入基因名或变异,返回临床意义分类(致病/良性/意义不明),for clinical variant interpretation. 用于变异临床解读。
Inputs: query (required), max_results. Returns: result
compound_infoB
Query compound/drug basic info (PubChem). 查询化合物/药物基本信息:分子式、分子量、规范 SMILES、IUPAC 名、InChIKey 与 CID,for medicinal chemistry and docking prep. 用于药物化学、分子对接前的化合物确认。
Inputs: name (required), include_synonyms. Returns: result
db_health_checkA
Check which bioinformatics databases are currently reachable. 检查各生物数据库端点的连通性:对每个数据库做真实 HTTP 请求,如实报告可达/不可达与状态码,不做乐观假设。返回结果用于确认当前环境下哪些数据库可用。
Inputs: timeout. Returns: result
dbsnp_searchA
Search NCBI dbSNP genetic variants. 检索 NCBI dbSNP 遗传变异:按基因/位置/rs 编号(如 'BRCA1[Gene Name] AND Homo sapiens[Organism]'、'rs1800057[RS]'),returns rsID/chromosome/position/alleles/clinical significance. 返回 rs 编号、染色体、位置、等位基因与临床意义。
Inputs: query (required), max_results. Returns: result
emdb_structure_lookupA
Look up EBI EMDB cryo-EM structure entry. 查询 EMDB 冷冻电镜结构:输入 EMD 编号(如 EMD-1234),returns title/authors/resolution/macromolecules/dates. 返回标题、作者、分辨率、组分与发布信息,用于电镜结构研究。
Inputs: emdb_id (required). Returns: result
ena_sequence_searchB
Search EBI ENA nucleotide sequences (microbes/viruses/plasmids). 检索 ENA 欧洲核苷酸档案核酸序列(微生物/病毒/质粒):输入物种或关键词(如 tax_tree(562) 大肠杆菌、tax_tree(2697049) 新冠),returns accession/description/organism/tax_id. 返回序列登录号、描述、物种与分类号,用于微生物与核酸研究。
Inputs: query (required), max_results. Returns: result
ensembl_gene_lookupB
Look up gene by symbol in Ensembl. 按基因符号查询 Ensembl 基因信息:Ensembl ID / chromosome location / biotype / description (GRCh38). Ensembl ID、染色体位置、生物型、描述,用于确认官方 ID 与坐标(GRCh38)。
Inputs: symbol (required), species. Returns: result
ensembl_homologsA
Query homologous genes (orthologs/paralogs) from Ensembl Compara. 查询基因的同源基因(直系同源/旁系同源),返回物种、同源基因 ID、序列一致性,for evolutionary analysis and model organisms. 用于进化分析、模式生物研究。
Inputs: symbol (required), species, target_species. Returns: result
europepmc_searchA
Full-text literature search (Europe PMC, EBI). 全文文献检索:比 PubMed 多了开放获取(OA)全文,returns title/journal/authors/DOI/open-access status. 返回标题、期刊、作者、DOI、是否可获取全文,适合做文献综述。
Inputs: query (required), max_results. Returns: result
expression_atlas_experimentA
Search Expression Atlas experiments by keyword. Input: search term (cancer, tissue, disease). Output: matching experiments with conditions, species, and data availability. 按关键词搜索表达实验:输入搜索词(cancer/tissue/TP53),返回匹配实验列表,包含物种、实验类型与样本数,用于数据发现。
Inputs: term (required). Returns: result
expression_atlas_geneA
Find Expression Atlas experiments relevant to a gene. Public REST no longer exposes numeric per-gene expression values; this returns experiments whose description/species match the gene (e.g. TP53, ENSG00000141510), where expression can be viewed. 查找与基因相关的表达实验:输入基因 ID 或符号(TP53/ENSG00000141510)与可选物种,返回匹配的表达实验列表。公开 REST 已不提供单基因数值表达量端点,此处诚实返回相关实验供进一步查看。
Inputs: gene_id (required), species. Returns: result
flybase_geneA
Get Drosophila gene by FlyBase ID. 按 FlyBase ID 获取果蝇基因信息:输入果蝇基因编号(如 FBgn0000015),返回基因名称、符号、染色体位置、功能注释与别名,用于果蝇遗传学研究。
Inputs: gene_id (required). Returns: result
flybase_searchA
Search Drosophila genes by keyword. 按关键词搜索果蝇基因:输入搜索词(基因名、功能或符号),返回匹配基因列表,包含基因 ID、符号与名称,用于基因发现。
Inputs: term (required). Returns: result
gene_enrichmentB
Gene ontology / pathway enrichment analysis (Enrichr engine). 对基因列表做 GO/KEGG/Reactome 通路富集分析,返回显著富集项(通路名/p值/校正p值/重叠基因)。For functional interpretation of omics / single-cell DEGs. 用于转录组/蛋白组/单细胞差异基因功能解读。
Inputs: genes (required), library, max_terms. Returns: result
gene_full_profileA
Combined multi-database gene analysis (cross-validation). 基因综合分析(多数据库交叉验证):给定基因符号,一次并发返回Ensembl 定位 + UniProt 蛋白注释 + STRING 互作伙伴 + PubMed 文献数,for project kickoff and functional overview. 适合开题调研、蛋白功能概述。
Inputs: symbol (required), species. Returns: result
gene_go_annotationB
Get GO annotations for a gene product. 按基因产品 ID 查询其基因本体(GO)注释:输入如 UniProtKB:P04637(TP53),返回该基因的 GO 注释列表(GO ID、方面、限定词与证据),用于功能理解与富集分析。
Inputs: gene_product_id (required), limit, aspect. Returns: result
genome_assembly_searchA
Search NCBI Assembly genome assemblies (bacteria/virus/eukaryote). 检索 NCBI Assembly 基因组组装(微生物/细菌/病毒/真核):输入物种或组装名(如 'Escherichia coli[Organism]'、'SARS-CoV-2[Organism]'),returns accession/name/organism/type/status. 返回组装编号、名称、物种、组装类型与状态,用于基因组学研究。
Inputs: query (required), max_results. Returns: result
geo_dataset_searchA
Search NCBI GEO gene expression datasets. 检索 NCBI GEO 基因表达数据集:按疾病/组织/实验类型(如 breast cancer、RNA-seq),returns GSE accession/title/platform/sample count/summary. 返回 GSE 编号、标题、平台、样本数与摘要,用于表达谱研究找数据。
Inputs: query (required), max_results. Returns: result
get_analysis_templateA
获取常见分析场景的模板方案。输入:场景类型(基因研究/药物发现/疾病分析等)。输出:模板化的分析流程和工具列表。
Inputs: scenario (required). Returns: result
glycan_lookupA
Look up a glycan structure by GlyTouCan accession. 按 GlyTouCan 编号查询糖苷结构:输入编号(如 G00051MO),returns composition/mass/monosaccharide count/sequence info. 返回糖苷组成、质量、单糖数与结构信息,用于糖组学研究。
Inputs: glytoucan_ac (required). Returns: result
go_term_lookupA
Look up a Gene Ontology term by GO ID. 按 GO 编号查询基因本体(GO)术语详情:输入 GO ID(如 GO:0006915),返回术语名称、所属方面(生物学过程/分子功能/细胞组分)、定义与同义词,用于理解基因功能注释含义。
Inputs: go_id (required). Returns: result
go_term_searchA
Search Gene Ontology terms by keyword. 按关键词搜索基因本体(GO)术语:输入英文关键词(如 apoptosis / kinase / membrane),返回匹配的 GO 术语列表,含编号、名称与所属方面,用于功能注释与富集分析。
Inputs: keyword (required), limit. Returns: result
gwas_gene_variantsA
Get GWAS variants associated with a gene. 按基因查询全基因组关联(GWAS)研究中与该基因关联的变异:输入基因符号(如 TP53),返回关联变异 rsID 列表,用于基因-变异-疾病关联研究。
Inputs: gene (required), limit. Returns: result
gwas_variant_associationsA
Get GWAS associations for a variant by rsID. 按 rsID 查询变异的全基因组关联(GWAS)关联:输入 dbSNP 编号(如 rs73229090),返回该变体的关联性状、p 值、风险等位基因频率与效应量,用于遗传关联解读与孟德尔随机化(MR)研究。
Inputs: rsid (required). Returns: result
hgnc_gene_symbolA
Get detailed human gene information by HGNC approved symbol. Input: gene symbol (BRCA1, TP53). Output: Complete gene nomenclature data including aliases, chromosomal location, and previous symbols.
Inputs: symbol (required). Returns: result
hgnc_searchA
Search human gene nomenclature by symbol or name. Input: gene symbol (BRCA1) or name keyword. Output: HGNC gene information with approved symbols, names, and aliases.
Inputs: query (required). Returns: result
intact_interactionsA
Search EBI IntAct experimentally-validated molecular interactions. 检索 IntAct 实验分子互作:输入基因或蛋白(如 TP53、P04637),returns interacting partners/detection method/evidence. 返回互作伙伴、检测方法与文献证据,用于验证蛋白互作网络。
Inputs: query (required), max_results. Returns: result
intelligent_analyzeB
智能分析生物数据并推荐最佳分析方案,节省token使用。输入:数据字符串,可选分析目标。输出:数据类型识别、推荐工具、预期结果、insights等。
Inputs: user_input (required), analysis_goal. Returns: result
kegg_pathway_genesA
List genes in a KEGG pathway. 查询 KEGG 通路包含的基因列表(如 hsa05224=Breast cancer),returns the genes in the pathway. 返回该通路下的基因,用于了解通路的分子组成。
Inputs: pathway_id (required). Returns: result
kegg_pathway_searchA
Search KEGG pathways by keyword. 按关键字搜索 KEGG 通路(如 'breast cancer'、'apoptosis'),returns pathway IDs and names. 返回通路 ID 与名称,用于找到目标通路编号。
Inputs: keyword (required). Returns: result
lipid_lookupA
Look up LIPID MAPS lipid structure by LM ID. 按 LIPID MAPS 编号查询脂质结构:输入 LM 编号(如 LMFA01030001 花生四烯酸、LMGP01010001 磷脂酰胆碱),returns name/formula/SMILES/InChIKey/DB cross-refs. 返回名称、分子式、SMILES 与数据库交叉引用,用于脂质组学研究。
Inputs: lm_id (required). Returns: result
metabolomics_latestB
List latest EBI Metabolights metabolomics studies. 列出 Metabolights 最新的代谢组学研究编号,returns MTBLS accession list for browsing. 返回最新研究编号列表,便于浏览代谢组学数据。
Inputs: limit. Returns: result
metabolomics_studyA
Get EBI Metabolights metabolomics study details. 查询 Metabolights 代谢组学研究:按 MTBLS 编号(如 MTBLS1),returns title/description/technology/design/factors. 返回研究标题、描述、检测技术(NMR/质谱)、实验设计与因子。
Inputs: study_id (required). Returns: result
microbiome_study_searchA
Search EBI MGnify microbiome metagenomics studies. 检索 MGnify 微生物组研究(细菌/古菌/病毒宏基因组):输入宿主或栖息地(如 gut microbiome、human、soil),returns study accession/name/samples/bioproject. 返回研究编号、名称、样本数与生物项目,用于微生物组学研究。
Inputs: query (required), max_results. Returns: result
ncbi_fetch_sequenceB
Download nucleotide/protein sequences (FASTA) from NCBI. 从 NCBI 下载核酸/蛋白序列(FASTA),支持 accession、gene symbol、关键词。DB options: nucleotide/gene/protein. 数据库可选 nucleotide/gene/protein,for getting reference sequences for downstream analysis. 用于获取参考序列做下游分析。
Inputs: query (required), db, max_ids, rettype. Returns: result
openalex_work_searchA
Search OpenAlex scholarly works. 检索 OpenAlex 学术文献:输入主题或关键词(如 CRISPR gene editing、organ-on-chip),returns title/year/citations/authors/venue. 返回标题、年份、被引、作者与期刊,用于文献调研与引用分析。
Inputs: query (required), max_results. Returns: result
pdb_structure_summaryC
Get protein structure summary from PDB. 按 PDB ID 获取蛋白质结构摘要:title/resolution/method/organism/deposition date and chain sequence. 标题/分辨率/实验方法/物种/沉积日期及指定链序列,for structural biology and drug design. 用于结构生物学、药物设计的结构查询。
Inputs: pdb_id (required), chain_id. Returns: result
plant_gene_lookupA
Look up plant gene information via Ensembl Plants. Input: gene symbol (e.g. AT1G01010, AGL1), plant species (e.g. arabidopsis/rice/maize/wheat/soybean). Output: gene ID, description, biotype, genomic location. 植物基因查询:通过 Ensembl Plants 查询植物基因信息(拟南芥/水稻/玉米/小麦/大豆等)。
Inputs: symbol (required), species. Returns: result
plant_species_listA
List supported plant species for BioMCP plant gene lookup. Input: none. Output: common plant species names mapped to Ensembl species IDs. 列出支持的植物物种及其对应 Ensembl 物种名。
Inputs: no named parameters. Returns: result
plasmid_searchA
Search NCBI plasmid sequences. 检索 NCBI 质粒序列:按质粒名称或宿主(如 'pET-28a[Title]'、'plasmid[Title] AND Escherichia coli[Organism]'),returns accession/title/organism/length. 返回质粒编号、名称、宿主与长度,用于分子克隆与载体设计。
Inputs: query (required), max_results. Returns: result
pride_projectA
Get PRIDE proteomics project by ID. 按项目 ID 获取蛋白质组学项目:输入 PXD 项目编号(如 PXD000001),返回项目标题、摘要、物种、实验类型与数据文件,用于蛋白质组学数据获取。
Inputs: project_id (required). Returns: result
pride_searchA
Search PRIDE proteomics projects by keyword. 按关键词搜索蛋白质组学项目:输入搜索词(如 cancer/human/tissue),返回匹配项目列表,包含项目标题、物种与数据访问链接,用于数据发现。
Inputs: keyword (required). Returns: result
protein_domainsB
Query protein structural domains from InterPro. 查询蛋白的 InterPro 结构域/家族/位点注释(输入 UniProt accession),returns domain name/type for functional region analysis. 返回结构域名、类型与位置,用于蛋白功能区域分析。
Inputs: uniprot_acc (required). Returns: result
protein_glycosylationA
Look up protein glycosylation and glycan sites. 查询蛋白的糖基化信息:按 UniProt 编号(如 P04637),returns protein names/glycosites/glycan modifications. 返回蛋白名称、糖基化位点与糖修饰信息,用于糖蛋白研究。
Inputs: uniprot_acc (required). Returns: result
protein_tissue_expressionB
Get Human Protein Atlas tissue expression profile. 查询蛋白组织表达图谱:按 Ensembl 基因号(如 ENSG00000141510),returns tissue-specific RNA/protein expression and localization. 返回组织特异性表达、亚细胞定位、蛋白分类与疾病关联。
Inputs: ensembl_id (required). Returns: result
pubmed_searchB
Search PubMed biomedical literature. 检索 PubMed 生物医学文献,returns title/authors/journal/year/PMID/DOI for literature review, grant proposals and evidence-based search. 返回标题/作者/期刊/年份/PMID/DOI,用于文献综述、开题、课题调研、循证检索。Use PubMed query syntax for term (e.g. 'BRCA1 AND breast cancer[Title]').
Inputs: term (required), sort_by, max_results. Returns: result
reactome_pathway_searchA
Search Reactome biological pathways. 检索 Reactome 生物通路:输入通路名或生物过程(如 apoptosis、glycolysis、DNA repair),returns stId/name/species/summation. 返回通路编号、名称、物种与摘要,用于信号转导与代谢通路研究。
Inputs: query (required), species, max_results. Returns: result
rgd_gene_symbolA
Get rat gene by gene symbol. 按基因符号获取大鼠基因信息:输入大鼠基因符号(如 Brca1/Tp53),返回基因名称、符号、染色体位置、功能注释与别名,用于大鼠遗传学研究。
Inputs: symbol (required). Returns: result
rgd_searchA
Search rat genes by keyword. 按关键词搜索大鼠基因:输入搜索词(基因名、功能或符号),返回匹配基因列表,包含基因符号、名称与 RGD ID,用于基因发现。
Inputs: term (required). Returns: result
sra_searchA
Search NCBI SRA sequence read archive (raw sequencing data). 检索 NCBI SRA 序列读取档案:按基因/物种/测序策略(如 RNA-seq[Strategy] AND cancer),returns run accession/study/sample/organism/strategy/platform. 返回测序运行编号、研究、样本、物种、策略与平台,用于查找原始测序数据。
Inputs: query (required), max_results. Returns: result
string_interactionsB
Query protein interaction network from STRING-db. 查询蛋白互作网络(STRING-db):给定一个或多个蛋白,返回互作关系及分数(综合分数越高越可信),for protein functional network analysis. 用于蛋白功能网络分析。
Inputs: proteins (required), species. Returns: result
taxonomy_lookupA
Look up NCBI Taxonomy species classification. 查询 NCBI Taxonomy 物种分类:输入物种名或 taxid(如 9606、human),returns scientific/common name, rank and lineage. 返回学名、常用名、分类层级与谱系,用于确认物种的官方分类。
Inputs: query (required). Returns: result
tool_inventoryA
List all BioMCP tools with their data source and verification status. 列出全部 BioMCP 工具及其数据源、验证状态(e2e_verified 已端到端验证 / best_effort 尽力而为未验证),并标注需要额外配置的工具。用于了解每个工具的可信度,避免过度信任未经证实的端点。
Inputs: no named parameters. Returns: result
ucsc_genome_infoC
Query UCSC Genome Browser. 查询 UCSC 基因组浏览器信息:list available genome assemblies or inspect one (e.g. hg38/GRCh38) and its gene annotation tracks. 列出可用组装,或查看某组装及其基因注释轨道,for genomics research. 用于基因组学研究。
Inputs: assembly, list_tracks. Returns: result
unichem_mappingA
Query compound identifier mapping across databases by InChIKey. 按 InChI Key 查询化合物在多个数据库(ChEMBL/PubChem/DrugBank/ChEBI 等)中的标识符映射:输入标准化化学标识符 InChI Key,返回该化合物在各化学数据库中的对应 ID,用于跨数据库化合物查询与整合。
Inputs: inchikey (required). Returns: result
unichem_structureA
Look up compound cross-references by InChI Key via UniChem. 按 InChI Key 查询化合物的跨库引用详情:返回该化合物在 UniChem 登记的化学数据库及对应标识符(来源/ID 列表),用于结构与标识符验证。
Inputs: inchikey (required). Returns: result
uniparc_by_idA
Get UniParc record details by UPI ID. 按 UPI 编号查询 UniParc 记录详情:输入 UPI 编号(如 UPI0000123165),returns sequence length/sequence/cross-references. 返回序列长度、序列本体与全部交叉引用数据库。
Inputs: upi (required). Returns: result
uniparc_searchB
Search EBI UniParc protein sequence archive. 检索 UniParc 蛋白序列归档:按物种/基因/蛋白编号,returns UPI IDs/cross-references/organism counts. 返回 UPI 编号、交叉引用数据库与物种信息,覆盖所有公开蛋白序列。
Inputs: query (required), max_results. Returns: result
uniprot_annotateA
Query UniProt protein annotations. 查询 UniProt 蛋白注释:protein name/gene/organism/length/function/Gene Ontology. 蛋白名/基因/物种/长度/功能/GO 项,支持 accession(如 P04637)或基因名检索,for protein function interpretation. 用于蛋白功能解读。
Inputs: query (required), max_results. Returns: result
variant_annotateA
Annotate human genetic variants (MyVariant.info). 注释人类基因变异:输入 HGVS(如 chr13:g.32911145G>A)或 rsID,returns allele frequency (GnomAD/1000G), functional predictions (SIFT/PolyPhen), gene and clinical significance. 返回人群频率、功能预测、基因与临床意义,for variant interpretation. 用于变异解读。
Inputs: variant (required). Returns: result
wormbase_geneA
Get C. elegans gene by WormBase ID. 按 WormBase ID 获取线虫基因信息:输入线虫基因编号(如 WBGene00000001),返回基因名称、符号、染色体位置、功能注释与序列信息,用于线虫生物学研究。
Inputs: gene_id (required). Returns: result
wormbase_searchA
Search C. elegans genes by keyword. 按关键词搜索线虫基因:输入搜索词(基因名、功能或符号),返回匹配基因列表,包含基因 ID、符号与名称,用于基因发现。
Inputs: term (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 73 tools
Multiple tools have nearly interchangeable roles, especially biogrid_interactions vs. biogrid_gene_interactions, hgnc_search vs. hgnc_gene_symbol, and unichem_mapping vs. unichem_structure. Protein interaction data can also be obtained from string_interactions or intact_interactions, while literature search is split across pubmed_search, europepmc_search, and openalex_work_search. Although many database-prefixed searches are distinct, these overlapping boundaries make selection error-prone.
Nearly all names use lower_snake_case and most follow a source-prefix pattern, but the action suffix is not standardized: search, lookup, query, annotate, fetch, and get are used inconsistently, and some names like pdb_structure_summary or protein_tissue_expression have no clear action. The pattern is readable but not predictable enough to support high-confidence selection.
73 tools is far beyond the practical agent context size for reliable selection, even for a broad bioinformatics utility. Many tools could be consolidated, such as merging the BioGRID, UniChem, and HGNC search/detail pairs. The count overwhelms rather than clearly earning each tool's place.
The set covers an unusually broad range of life-science domains, including genes, proteins, variants, literature, structures, pathways, interactions, compounds, model organisms, and multi-omic data repositories. Minor gaps remain, such as no direct retrieval of full expression matrices or raw sequence files from search results, but the search-and-annotate surface is generally adequate.
Maintenance
Related MCP Connectors
MCP gateway federating 26 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.
AI-powered bioprotocol optimization — generate, search, and manage lab protocols via MCP
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
Connect AI clients to biomedical data and tools.
Related MCP Servers
- AlicenseBqualityBmaintenanceAn MCP server that provides standardized access to biomedical knowledge bases and resources, enabling AI systems to retrieve verified information from sources like bioRxiv, EuropePMC, and various protein/gene databases.5233Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA unified MCP server for biomedical research that connects AI systems to resources like Ensembl, EuropePMC, STRING, and more, enabling retrieval of verified domain-specific information.Apache 2.0
- AlicenseAqualityBmaintenanceA high-performance MCP server that gives LLMs access to 25 biomedical tools federated across 50+ upstream APIs for genes, variants, drugs, diseases, literature, clinical trials, and structural biology.43138 npm12Apache 2.0
- AlicenseNot gradedqualityCmaintenanceUnified MCP server providing AI-agent-ready access to AlphaFold, PubMed, ChEMBL, Ensembl, and 37+ scientific databases.MIT