Log inSubmit server
BioMCP TS logo

BioMCP TS

Federated MCP access to biomedical databases for genes, variants, drugs, diseases, literature, trials, structures, patents, and GEO.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install BioMCP TS

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "biomcp-ts": {
      "command": "npx",
      "args": [
        "-y",
        "biomcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

BioMCP-TS connects AI agents to federated biomedical, pharmaceutical, literature, clinical-trial, patent, and structural-biology data sources. Its MCP tools cover gene, variant, drug, disease, article, trial, PDB, patent, and NCBI GEO searches, detailed lookups, enrichment, and batch retrieval. Run it as a zero-configuration stdio server with Node.js 22.13 or newer, or use optional configuration for features such as OncoKB annotations. Reach for it when an agent needs to resolve biological concepts and combine evidence across multiple research databases.

Use cases

  • Investigate gene–disease and gene–drug relationships
  • Compare variants with clinical, frequency, and cancer annotations
  • Search literature and retrieve eligible article or preprint full text
  • Find relevant clinical trials by disease, gene, drug, or variant
  • Review patents, protein structures, and functional-genomics studies

Key features

  • Federated biomedical and literature search
  • Gene, variant, drug, and disease relationship lookups
  • Clinical-trial, patent, PDB, and GEO retrieval
  • Reactome pathway enrichment
  • On-demand article and preprint full-text access
  • Parallel multi-entity retrieval

Tools54

What BioMCP TS lets your agent do. Expand a tool for its parameters.

Self-reported~2.4k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

10/10 checks healthy over the last 50d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · biomcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars12Stargazers on the source repository.
npm downloads840Package downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Tools exposed54Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How BioMCP TS works

What BioMCP-TS does

BioMCP-TS provides MCP tools for querying biomedical and biopharmaceutical information from multiple public and specialized sources. Its entity coverage includes genes, genetic variants, drugs, diseases, research articles, clinical trials, protein structures, patents, and NCBI GEO functional-genomics studies.

The server supports both discovery and follow-up retrieval. Agents can search by natural-language concepts or domain identifiers, resolve concepts across entity types, request selected detail sections, and retrieve several entities in parallel. Gene tools include alias-aware lookup, disease and drug associations, clinical trials, literature, and Reactome pathway enrichment. Variant tools support identifiers such as rsIDs and HGVS expressions, along with ClinVar significance, frequency, CADD, predictions, and clinical information.

How it works

BioMCP-TS exposes the data sources through MCP tool calls and federates several searches across backends. Literature search can query PubMed, Europe PMC, Semantic Scholar, arXiv, PubTator, and LitSense; a preprint-only mode targets bioRxiv and medRxiv. Article retrieval accepts PMIDs, PMCIDs, DOIs, and preprint DOIs. Freely readable full text can be returned inline with a character cap or written to a server-side Markdown file with an outline for selective reading.

Preprint full text is fetched only on demand, parsed from JATS XML, and cached by DOI and version. Downloads are paced to respect source limits, and rate-limit responses expose retry information. Federated responses can preserve warnings and backend errors separately from result records, which helps agents distinguish partial results from empty searches.

Clinical-trial searches support cursor pagination, while patent searches cover worldwide authorities and can filter by assignee, inventor, CPC, status, and date. The PDB tool handles structure searches, metadata, and mmCIF or PDB downloads.

Setup and configuration

The package runs with Node.js 22.13 or newer. Use the following commands to check the local environment and start the standard MCP process:

Terminal
npx -y biomcp doctor
npx biomcp

The second command starts a zero-configuration stdio server for MCP clients. A shared biomcp serve daemon is available for setups with multiple agents on one machine, allowing them to share process-level rate limiting. OncoKB variant annotations require the ONCOKB_TOKEN environment variable.

Optional toolboxes support local database curation and dependency-free analysis using Bioconductor and SAM/BED/BCFtools without requiring an R installation, C toolchain, or containers.

Tools and capabilities

  • Search and inspect genes, variants, drugs, diseases, articles, trials, patents, PDB structures, and GEO studies.
  • Resolve free-text biomedical concepts with discover and retrieve multiple entities concurrently with batch_get.
  • Run Reactome enrichment for gene lists and query gene, disease, drug, and variant relationships.
  • Search federated literature sources, inspect citation graphs and article metadata, and retrieve eligible full text.
  • Query clinical trials by condition, intervention, status, phase, gene, variant, drug, or disease.
  • Retrieve regulatory, safety, target, indication, adverse-event, patent, structure, and functional-genomics information through specialized tools.

Limitations and notes

Data availability depends on the upstream source used by each tool. Some responses may contain backend warnings or errors alongside usable results. AlphaGenome scores in variant_get currently return an unavailable status. Full article text is limited to freely readable content in supported repositories, and preprint retrieval is subject to source rate limits and article-specific licenses.

For multiple local MCP processes, arXiv request limits are not coordinated between processes. A shared daemon is the intended arrangement when several agents need to use the service on one machine.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about BioMCP TS

BioMCP-TS is an MCP server that connects AI agents to biomedical, pharmaceutical, literature, clinical-trial, patent, PDB, and GEO data sources. Its main tools search and retrieve genes, variants, drugs, diseases, articles, trials, structures, and patents, with additional concept discovery, batch retrieval, and gene-list pathway enrichment.

Install and start BioMCP-TS with `npx biomcp`; it runs as a zero-configuration stdio MCP server. Use `npx -y biomcp doctor` first to check Node.js, configuration health, feature gates, and dependencies. Node.js 22.13 or newer is required.

Yes, BioMCP-TS works with Claude Desktop through its stdio MCP server. The project provides client configuration guidance for Claude Desktop, and the standard `npx biomcp` command is the process clients run.

Set the `ONCOKB_TOKEN` environment variable before using `variant_oncokb`. That tool uses the token to retrieve OncoKB cancer variant annotations; the other listed variant search and retrieval tools do not require this token.

Yes, when supported content is freely readable. `article_get` can return eligible PMC or Europe PMC text inline or write it to a server-side Markdown file, while `preprint_fulltext` fetches bioRxiv or medRxiv JATS content on demand with version-aware caching and rate limiting.

Related MCP servers

All in Biology & Bioinformatics All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewBioMCP TS AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/biomcp-ts?style=directory)](https://allmcps.com/mcp/biomcp-ts)
HTML Embed
<a href="https://allmcps.com/mcp/biomcp-ts"><img src="https://allmcps.com/api/badge/biomcp-ts?style=directory" alt="BioMCP TS on AllMCPs" /></a>