convez.ai
MCP ServerBusca & PesquisaAvançado
SachinGawande2003

Heuris-BioMCP

SachinGawande2003/Heuris-BioMCP

MCP server para bioinformática com 32 ferramentas e integração a bases de dados biológicas

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP especializado em bioinformática e ciências da vida que integra ferramentas de pesquisa, análise de drogas, triagem clínica e biologia computacional. Fornece 32 ferramentas curadas e acesso a 30+ bases de dados biológicas para suportar workflows de pesquisa e revisão translacional.

Instalação

$npx convez-ai SachinGawande2003/Heuris-BioMCP

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
57%
Último commit
há 7 meses
Versão
—
Issues abertas
0
Contribuidores
2

Casos de uso

  • Pesquisa de alvos farmacológicos e descoberta de drogas
  • Análise de variantes genômicas e caminhos metabólicos
  • Triagem de ensaios clínicos e segurança farmacológica
  • Diagnóstico de doenças raras e análise proteômica

Veredito

Projeto maduro e bem arquitetado para pesquisadores e sistemas de análise biomédica. A curação de 32 ferramentas em torno de workflows reais (descoberta de drogas, genômica, ensaios clínicos) e integração com ChEMBL, ClinicalTrials.gov e outras bases consolidadas o tornam produtivo para contextos científicos sérios, embora requeira familiaridade com conceitos de bioinformática.

README

A tradução para o português deste README ainda está na fila.

🧬 Heuris-BioMCP — Bioinformatics Model Context Protocol Server

License: MIT Python 3.11+ MCP Compatible Tools: 32 Databases: 30+ Live Demo

Strategic Model Context Protocol server for life sciences.
Connect ChatGPT, Claude, and other MCP clients to a curated biology tool surface built for research, translational workflows, and production review.

🚀 Quick Start • 🔧 Tools • 📊 Databases • 💡 Examples • 🤝 Contributing


Live Demo

Try Heuris-BioMCP without installing — connect to our live server:

https://heuris-biomcp.onrender.com/mcp

If hosted auth is enabled, Claude-compatible clients will complete the OAuth redirect flow automatically. Non-interactive clients can also use bearer API keys.

Connect to Live Server

For Claude, use Customize > Connectors and enter:

https://heuris-biomcp.onrender.com/mcp

For generic remote MCP clients that accept URL-based server definitions:

{
  "mcpServers": {
    "heuris-biomcp": {
      "url": "https://heuris-biomcp.onrender.com/mcp"
    }
  }
}

Note: https://heuris-biomcp.onrender.com/mcp is the recommended remote MCP endpoint for modern clients. The legacy SSE endpoint remains available at https://heuris-biomcp.onrender.com/sse.


See Heuris-BioMCP in Action

Heuris-BioMCP Demo

Quick Demo Video

Watch how to connect Heuris-BioMCP to Claude Desktop:

Tip: Coming soon - video walkthrough of connecting Heuris-BioMCP and running your first query!


What is Heuris-BioMCP?

Heuris-BioMCP bridges MCP clients and high-value life-science data sources through a curated public tool surface. The server exposes the workflows that matter most for product review and research use, while lower-level helper modules remain internal for composition and planner logic.

You -> "What drugs target EGFR and what clinical trials are recruiting?"
ChatGPT + Heuris-BioMCP -> Queries ChEMBL + ClinicalTrials.gov -> Structured answer

What's New in v2.3

  • Curated the public MCP surface from a broad 71-tool registry down to a strategy-driven set of 32 review-friendly tools
  • Merged operational suites into workflow tools: find_protein, pathway_analysis, crispr_analysis, drug_safety, variant_analysis, and session
  • Added new translational tools: drug_interaction_checker, protein_binding_pocket, biomarker_panel_design, pharmacogenomics_report, protein_family_analysis, network_enrichment, rnaseq_deconvolution, structural_similarity, rare_disease_diagnosis, and genome_browser_snapshot
  • Removed low-signal or niche tools from the public MCP registry while keeping lower-level code available internally
  • Preserved hosted HTTP/SSE deployment and operational endpoints for production-style MCP review
  • Added optional hosted OAuth 2.1 PKCE and API-key auth for authenticated remote connectors
  • Added Prometheus metrics, streamed progress chunks for slow tools, persistent gene/disease/watch MCP resources, and literature watch workflows

Tools (32 curated public surface)

Core Research

ToolDescription
search_pubmedPubMed literature search with MeSH, Boolean syntax, abstracts, and metadata
get_gene_infoNCBI Gene summary with aliases, locus, and functional context
run_blastNCBI BLAST sequence alignment
get_protein_infoFull UniProt Swiss-Prot protein record
find_proteinUnified UniProt plus PDB protein discovery workflow
get_alphafold_structureAlphaFold structure metadata and confidence summary
pathway_analysisMerged KEGG plus Reactome pathway workflow
get_drug_targetsChEMBL drug-target evidence for a gene
get_gene_disease_associationsOpen Targets translational gene-disease evidence
search_clinical_trialsClinicalTrials.gov recruiting-trial search
multi_omics_gene_reportIntegrated multi-database flagship gene report

AI And Engineering Workflows

ToolDescription
predict_structure_boltz2Boltz-2 structure workflow with optional protein-ligand mode
generate_dna_evo2Evo2 generation or WT-vs-variant scoring workflow
crispr_analysisMerged CRISPR design, scoring, off-target, base-edit, and repair workflow
drug_safetyMerged FDA safety workflow for events, signals, labels, and comparisons
variant_analysisMerged ACMG, gnomAD, ClinVar, splice, and integrated variant reporting
sessionMerged entity, graph, export, and adaptive planning workflow

High-Value Translational Tools

ToolDescription
find_repurposing_candidatesDrug repurposing workflow over literature, trials, and target evidence
verify_biological_claimCross-database biological claim verification
search_cbio_mutationsCancer mutation frequency search
search_gwas_catalogGWAS trait-association search
drug_interaction_checkerFDA label-based interaction screening
protein_binding_pocketCandidate binding-site summary from annotated protein features
biomarker_panel_designDisease-focused biomarker panel drafting
pharmacogenomics_reportCPIC-style pharmacogenomics summary with PGx evidence
protein_family_analysisProtein family and domain context
network_enrichmentGene-set pathway and interaction-hub enrichment summary
rnaseq_deconvolutionMarker-based bulk RNA-seq deconvolution
structural_similarityPubChem-based chemical structural similarity search
rare_disease_diagnosisPhenotype normalization plus OMIM-oriented rare-disease differential support
genome_browser_snapshotBrowser-ready locus context for genes and genomic intervals

Public Surface Policy

  • The MCP registry is intentionally curated.
  • Lower-level legacy implementations still exist in the package for internal orchestration and testing.
  • Reviewers should evaluate the exposed MCP surface, not the hidden implementation inventory.

Databases & AI Models

SourceDomainURL
Traditional Databases
NCBI PubMedLiteraturehttps://pubmed.ncbi.nlm.nih.gov
NCBI GeneGenomicshttps://www.ncbi.nlm.nih.gov/gene
NCBI BLASTSequence Alignmenthttps://blast.ncbi.nlm.nih.gov
NCBI GEOGene Expressionhttps://www.ncbi.nlm.nih.gov/geo
UniProt Swiss-ProtProteomicshttps://www.uniprot.org
AlphaFold DBProtein Structurehttps://alphafold.ebi.ac.uk
RCSB PDBProtein Structurehttps://www.rcsb.org
KEGGPathwayshttps://www.kegg.jp
ReactomePathwayshttps://reactome.org
ChEMBLDrug Discoveryhttps://www.ebi.ac.uk/chembl
Open TargetsGene-Diseasehttps://platform.opentargets.org
EnsemblGenomicshttps://www.ensembl.org
ClinicalTrials.govClinicalhttps://clinicaltrials.gov
Human Cell AtlasSingle-Cellhttps://data.humancellatlas.org
OpenNeuroNeuroimaginghttps://openneuro.org
NeuroVaultNeuroimaginghttps://neurovault.org
v2 Extended Databases
OMIMGenetic Diseaseshttps://www.omim.org
STRINGProtein Interactionshttps://string-db.org
GTExExpression Atlashttps://gtexportal.org
cBioPortalCancer Genomicshttps://www.cbioportal.org
GWAS CatalogTrait Associationshttps://www.ebi.ac.uk/gwas
DisGeNETDisease-Genehttps://www.disgenet.org
PharmGKBPharmacogenomicshttps://www.pharmgkb.org
v2.2 Tier 2 Databases
BioGRIDProtein Interactionshttps://thebiogrid.org
OrphanetRare Diseaseshttps://www.orpha.net
GDC / TCGATumor Genomicshttps://portal.gdc.cancer.gov
CellMarkerCell Type Markershttp://xteam.xbio.top/CellMarker
ENCODERegulatory Elementshttps://www.encodeproject.org
MetaboLightsMetabolomicshttps://www.ebi.ac.uk/metabolights
UCSC Genome BrowserSplice Isoformshttps://genome.ucsc.edu
Safety, Variant & Innovation Sources
OpenFDA / FAERSDrug Safetyhttps://api.fda.gov
DailyMedDrug Labelshttps://dailymed.nlm.nih.gov
ClinVarClinical Variantshttps://www.ncbi.nlm.nih.gov/clinvar
gnomADPopulation Variationhttps://gnomad.broadinstitute.org
bioRxiv / medRxivPreprintshttps://www.biorxiv.org
InterProProtein Domainshttps://www.ebi.ac.uk/interpro
COSMICCancer Mutationshttps://cancer.sanger.ac.uk/cosmic
AI Models (NVIDIA NIM)
MIT Boltz-2Structure Predictionhttps://build.nvidia.com/mit/boltz2
Arc Evo2-40BDNA Generationhttps://build.nvidia.com/arc/evo2-40b

Quick Start

Option 1: Use Live Demo (No Installation)

Use Claude's Customize > Connectors flow and enter:

https://heuris-biomcp.onrender.com/mcp

If you are connecting with an older MCP client that still expects SSE, use:

https://heuris-biomcp.onrender.com/sse

Option 2: Deploy Your Own

Deploy to Render with one click:

Deploy to Render

Or manually:

  1. Fork this repository
  2. Create a new Web Service on Render
  3. Connect your fork
  4. Set build command: pip install -r requirements.txt && pip install -e .
  5. Set start command: BIOMCP_TRANSPORT=http BIOMCP_HTTP_PORT=$PORT python -m biomcp

Hosted Deployment Limitations

  • Session snapshots saved through the session tool are only durable if BIOMCP_SESSION_STORE_DIR points to persistent storage.
  • On Render free tier, the default local directory uses ephemeral disk and will be wiped on restart, redeploy, or scale-to-zero wake-up.
  • If you need persistent saved sessions, set BIOMCP_SESSION_STORE_DIR to a mounted persistent path or move session persistence behind an external store before relying on cross-session restore.

Hosted Auth and Connector Setup

  • For Anthropic-style hosted connectors, enable BIOMCP_AUTH_ENABLED=1.
  • OAuth 2.1 PKCE is exposed at /.well-known/oauth-authorization-server, /oauth/authorize, /oauth/token, and /oauth/register.
  • For machine-to-machine clients, set BIOMCP_API_KEYS and send either Authorization: Bearer <key> or X-API-Key: <key>.
  • Per-key limits are controlled with BIOMCP_API_KEY_RATE_LIMIT_REQUESTS and BIOMCP_API_KEY_RATE_LIMIT_WINDOW_SECONDS.

Persistent Resources and Literature Watches

  • biomcp://gene/{SYMBOL} returns a curated gene context resource with gene, protein, pathway, disease, and drug-target context.
  • biomcp://disease/{URL-ENCODED-NAME} returns disease literature plus session-graph context.
  • session(action="watch") registers a PubMed + bioRxiv watch and exposes biomcp://watch/{TOPIC} as a reusable resource.
  • Saved sessions and watches are only persistent if the backing session-store directory is durable.

Privacy, Support, and Data Handling

Option 3: Local Installation

Prerequisites

  • Python 3.11+
  • Claude Desktop or any MCP-compatible client
  • (Optional) NCBI API key for higher rate limits
  • (Optional) NVIDIA API keys for AI tools

Installation

# Clone the repository
git clone https://github.com/SachinGawande2003/Heuris-BioMCP.git
cd Heuris-BioMCP

# Install (standard)
pip install -e .

# Install with neuroimaging support
pip install -e ".[neuroimaging]"

# Install with dev dependencies (recommended)
pip install -e ".[dev]"

Configure Claude Desktop

For Local STDIO Mode (default):

{
  "mcpServers": {
    "heuris-biomcp": {
      "command": "biomcp",
      "env": {
        "NCBI_API_KEY": "your_ncbi_api_key_here"
      }
    }
  }
}

For Remote HTTP Mode (using live demo or your own deployed server):

Use Claude's Customize > Connectors flow and enter:

https://heuris-biomcp.onrender.com/mcp

If you are connecting with an older MCP client that still expects SSE, use:

https://heuris-biomcp.onrender.com/sse

💡 Tip: Get a free NCBI API key to increase rate limits from 3 to 10 requests/second.

🚀 New: Get free NVIDIA API keys for AI tools at build.nvidia.com/mit/boltz2 and build.nvidia.com/arc/evo2-40b.

Restart Claude Desktop and test:

"Search PubMed for recent papers on CAR-T cell therapy in B-cell lymphoma"
"Get the AlphaFold structure for TP53 and tell me about the confidence scores"
"What drugs are approved that target EGFR?"
"Generate a multi-omics report for KRAS"
"Predict the structure of EGFR with ligand CC1=CC=CC=C1 and compute binding affinity"
"Generate a DNA sequence starting with ATGGCG..."

Usage Examples

Literature Mining

"Search PubMed for BRCA1 CRISPR correction methods published in the last 2 years"
"Find review articles about PD-1/PD-L1 immune checkpoint inhibitors"

Protein Analysis

"Get UniProt info for human TP53 (P04637) including its domains and disease associations"
"Search for AlphaFold structures for insulin receptor"
"Find all PDB crystal structures of BRAF kinase domain resolved below 2.5 Ångström"

Drug Discovery

"What are the top ChEMBL compounds targeting KRAS G12C mutation?"
"Get compound info for imatinib (CHEMBL941)"
"Show me gene-disease associations for BRCA1 with evidence scores"

AI-Powered Structure Prediction

"Predict the 3D structure of insulin (sequence: ...) with ligand CCO"
"Compute binding affinity between EGFR and gefitinib (SMILES: ...)"
"Get structure prediction for a protein-protein complex"

AI-Powered DNA Generation

"Generate a 200bp promoter sequence starting with ATG"
"Compare wildtype vs variant DNA sequence for TP53 mutation"
"Generate regulatory element for gene expression"

Multi-Omics Report (Flagship)

"Generate a complete multi-omics report for EGFR"

This single command queries 7 databases in parallel and returns:

  • Genomic location and gene summary (NCBI Gene)
  • Recent publications (PubMed)
  • Protein function and structure (UniProt + AlphaFold)
  • Biological pathways (Reactome)
  • Drug targets and clinical compounds (ChEMBL)
  • Disease associations with scores (Open Targets)
  • Expression datasets (GEO)
  • Active clinical trials (ClinicalTrials.gov)

v2 Extended Databases

"Get OMIM diseases associated with TP53"
"Show STRING protein interactions for EGFR"
"Get GTEx expression data for BRCA1 across tissues"
"Find mutations in TP53 from cBioPortal"
"Search GWAS for diabetes-associated SNPs"

v2 Verification

"Verify the claim that TP53 is a tumor suppressor gene"
"Detect conflicts between OMIM and DisGeNET for BRCA1"

v2 Experimental Design

"Generate an experimental protocol for CRISPR knockout of BRCA1"
"What cell lines should I use to study KRAS mutations?"
"Calculate sample size for detecting 2-fold change with p<0.05"

v2 Session Intelligence

"What's the knowledge graph from our conversation so far?"
"Find biological connections between TP53 and EGFR"
"Export our research session as a reproducible script"
"Plan and execute a research workflow for PD-1 drug targets"

Architecture

biomcp/
├── src/biomcp/
│   ├── server.py              # MCP server — tool registry & dispatcher
│   ├── tools/
│   │   ├── ncbi.py            # PubMed, Gene, BLAST
│   │   ├── proteins.py        # UniProt, AlphaFold, PDB
│   │   ├── pathways.py        # KEGG, Reactome, ChEMBL, Open Targets
│   │   ├── advanced.py        # ClinicalTrials, GEO, scRNA, Ensembl,
│   │   │                      # Multi-Omics, Neuroimaging, Hypothesis
│   │   ├── nvidia_nim.py      # Boltz-2, Evo2-40B AI models
│   │   ├── databases.py       # v2: OMIM, STRING, GTEx, cBioPortal,
│   │   │                      #      GWAS, DisGeNET, PharmGKB
│   │   ├── verify.py          # v2: Claim verification, conflict detection
│   │   └── protocol_generator.py  # v2: Experimental design tools
│   ├── core/
│   │   ├── entity_resolver.py # v2: Cross-database entity resolution
│   │   ├── knowledge_graph.py # v2: Session knowledge graph
│   │   └── query_planner.py   # v2: Adaptive query planner
│   └── utils/
│       └── __init__.py        # Rate limiter, cache, validators, HTTP client
├── tests/
├── pyproject.toml
└── README.md

Key design decisions:

  • Async-first: All API calls are fully async with httpx, never blocking
  • Rate limiting: Token-bucket limiter per service respects each API's limits
  • Smart caching: TTL-based per-namespace cache (1h literature, 7d structures)
  • Retry logic: Exponential backoff via tenacity for transient failures
  • Validation: Input validation before any network call — never wastes API quota

Environment Variables

VariableDescriptionDefault
NCBI_API_KEYNCBI API key (increases rate limit to 10/s)None (3/s)
NVIDIA_BOLTZ2_API_KEYNVIDIA API key for Boltz-2 structure predictionNone
NVIDIA_EVO2_API_KEYNVIDIA API key for Evo2-40B DNA generationNone
NVIDIA_NIM_API_KEYShared fallback key for both NVIDIA model integrationsNone
BIOGRID_API_KEYBioGRID key for curated interaction queriesNone
BIOMCP_TRANSPORTTransport mode: stdio or httpstdio
BIOMCP_HTTP_PORTHTTP port for hosted SSE deployments8080
BIOMCP_SESSION_STORE_DIRDurable directory for saved sessions.biomcp_sessions
BIOMCP_AUTH_ENABLEDRequire auth for hosted MCP requestsdisabled
BIOMCP_OAUTH_ENABLEDEnable OAuth 2.1 PKCE endpoints when auth is enabled1
BIOMCP_API_KEYSComma-separated API keys in key_id:secret formNone
BIOMCP_API_KEY_RATE_LIMIT_REQUESTSPer-key request budget per window600
BIOMCP_API_KEY_RATE_LIMIT_WINDOW_SECONDSPer-key rate-limit window in seconds60
BIOMCP_OAUTH_AUTO_APPROVEAuto-approve the consent screen for single-user deployments0
BIOMCP_OAUTH_DEFAULT_SUBJECTSubject bound to approved OAuth tokensheuris-biomcp-user
BIOMCP_CORS_ALLOW_ORIGINSComma-separated browser origins allowed for CORSdisabled
BIOMCP_HTTP_RATE_LIMIT_ENABLEDEnable per-client HTTP rate limiting1
BIOMCP_HTTP_RATE_LIMIT_REQUESTSRequests allowed per rate-limit window120
BIOMCP_HTTP_RATE_LIMIT_WINDOW_SECONDSRate-limit window length in seconds60
BIOMCP_HTTP_AUTH_RATE_LIMIT_REQUESTSRequests allowed per authenticated window600
BIOMCP_HTTP_AUTH_RATE_LIMIT_WINDOW_SECONDSAuthenticated rate-limit window length in seconds60
BIOMCP_CACHE_WARMINGEnable background cache warming in HTTP modeauto
BIOMCP_LOG_LEVELLog level: DEBUG/INFO/WARNING/ERRORINFO

Get free API keys:

Operational Endpoints

When BioMCP runs in hosted HTTP mode, these operational routes are available:

EndpointPurpose
/statusRuntime status, HTTP policy, and session-storage configuration
/metricsPrometheus-compatible request, cache, latency, auth, and upstream metrics
/healthzLiveness and deployment metadata
/readyzReadiness check for orchestrators and load balancers
/tool-healthCapability-level status, including missing optional API keys
/.well-known/oauth-authorization-serverOAuth 2.1 metadata for hosted connectors
/oauth/registerDynamic OAuth client registration
/oauth/authorizeOAuth authorization and PKCE consent
/oauth/tokenAuthorization-code and refresh-token exchange
/mcpStreamable HTTP MCP endpoint
/sseMCP SSE endpoint
/messages/MCP message transport endpoint

These endpoints are designed for deployment review, Render health checks, and production smoke tests.


Contributing

Contributions are welcome! Whether it's adding a new database, fixing a bug, improving documentation, or integrating new AI models.

# Development setup
pip install -e ".[dev]"

# Run tests
pytest tests/ -v --cov=biomcp

# Lint + type check
ruff check src/
mypy src/

Ideas for contributions

  • Add more pathway databases (Wikipathways, PathCards)
  • Integrate COSMIC for somatic mutations
  • Add protein complex data (CORUM)
  • Implement batch query support for high-throughput analysis
  • Add Jupyter notebook examples
  • Improve conflict resolution algorithms

Citation

If you use Heuris-BioMCP in your research, please cite:

@software{biomcp2025,
  title   = {Heuris-BioMCP v2: A Comprehensive MCP Server for Bioinformatics, AI Models, and Life Sciences},
  year    = {2025},
  url     = {https://github.com/SachinGawande2003/Heuris-BioMCP},
  license = {MIT}
}

License

MIT License — free for academic and commercial use.


Ver o original no GitHub

Bom para

Relacionados