M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
B

BioMCP

Community
One binary. One grammar. Evidence from the biomedical sources you already trust.
How to install ↓ Compare GitHub source repository ↗
Category
Other #2 of 230
Stars
★ 653 Very popular
Transport
stdio (local process) · Streamable HTTP
Runtime
Prebuilt binary · Docker · Python · Rust
Credentials
Optional API key
License
MIT
Last commit
Tools
11
75FMRS · B

BioMCP provides a powerful unified CLI and MCP server for biomedical data search, with broad entity support and local analysis features. MIT-licensed, no telemetry, privacy-focused. Suitable for researchers and clinicians needing efficient access to trusted biomedical data.

Strongest · Maintenance 18/20 Weakest · Reliability 10/20

Reliability
10/20
Security and permissions
16/20
Maintenance
18/20
Documentation
17/20
Setup experience
14/20
Why each score
Reliability 10/20
The server is described as read-only biomedical search via a PyPI package (biomcp-cli 0.8.25) using stdio. Static review shows clear structure and no open issues, but no executable CI configurations or test files are present in the provided source, so key paths' stability and error handling cannot be confirmed. README references make lint/test/spec but that is not verifiable evidence. Therefore reliability capped at 10.
Security and permissions 16/20
Explicitly read-only, no telemetry, credentials via env vars, no malicious patterns. HTTP host allow-list and self-update checksum option are present. No dangerous defaults or real tokens in install examples. Main risks are external API dependencies and local data processing, which are typical. Score 16.
Maintenance 18/20
Repository is active with recent releases (0.8.25), clear MIT license, no open issues, and an update mechanism. Governance seems healthy, though a dedicated security-response channel is not documented. Overall strong maintenance, so 18.
Documentation 17/20
Comprehensive docs: installation, configuration, usage examples, API keys, troubleshooting. README has multiple sections and links to detailed docs. Minor gaps: 'make verify' is referenced but not explicitly in the README, and cost/limitations are not covered. Documentation is solid with some hidden assumptions, so 17.
Setup experience 14/20
Multiple install methods: PyPI, Homebrew, Docker, source, and script. Client config examples provided. Paths are clear, but no verifiable execution evidence (CI) and source build may require extra steps. Given these, setup scored 14.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesWrites / deletes local filesUses the network

Best for

  • Biomedical researchers
  • Clinicians
  • AI agents that need efficient access to biomedical literature and data analysis

Not for

  • Users needing to write to upstream databases (read-only)
  • Users requiring direct access to closed datasets (e.g., COSMIC is not directly integrated)
  • Users expecting all advanced features without API keys

Required permissions

  • Requires internet access to query public biomedical APIs
  • Optional API keys (NCBI, Semantic Scholar, OpenFDA, etc.) to improve rate limits or unlock features
  • Local read/write access for skills, cache, and local study data (e.g., `~/.local/share/biomcp`)

Risks and side effects

  • Upstream API rate limits may affect performance
  • Some data sources (e.g., KEGG) have licensing terms that restrict non-academic use
  • Features requiring API keys (e.g., OncoKB) may be incomplete without them
  • Local binary installations need regular updates for compatibility

Setup

Before you start

Runtime：Prebuilt binary · Docker · Python · Rust

NCBI_API_KEY optionalsecret NCBI API key for improved rate limits on PubTator, PubMed/efetch, PMC OA, and NCBI ID converter; request via your NCBI account.
S2_API_KEY optionalsecret Semantic Scholar API key unlocking dedicated quota at 1 req/sec, improving reliability of article TLDR, citation, reference, and recommendation helpers.
OPENFDA_API_KEY optionalsecret OpenFDA API key raising rate limits for FAERS, MAUDE, drug labels, and related queries.
NCI_API_KEY optionalsecret NCI CTS API key, needed only for trial search with `--source nci`.
ONCOKB_TOKEN optionalsecret OncoKB access token enabling `biomcp variant oncokb` therapy and level-of-evidence lookups; obtain by registering with OncoKB.
ALPHAGENOME_API_KEY optionalsecret AlphaGenome API key for variant effect prediction.
DISGENET_API_KEY optionalsecret DisGeNET API key enabling scored gene-disease association sections on gene and disease lookups.
Other optional settings (1)
BIOMCP_STUDY_DIR optional Local study root directory for reproducible study command datasets; falls back to a default location if unset.
  1. Install: uv tool install biomcp-cli (or pip install biomcp-cli, or binary: curl -fsSL https://biomcp.org/install.sh | bash, or Homebrew: brew tap genomoncology/biomcp && brew install biomcp).
  2. Verify: biomcp health --apis-only.
  3. Configure MCP client: for Claude Desktop, use the JSON config; for Claude Code, use /plugin marketplace add genomoncology/biomcp and /plugin install biomcp@biomcp; for Codex, use codex mcp add biomcp -- biomcp serve.
  4. (Optional) Install skills: biomcp skill install ~/.claude --force.
claude_desktop_config.json 
{
  "mcpServers": {
    "biomcp": {
      "command": "biomcp",
      "args": ["serve"]
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "biomcp": {
      "command": "biomcp",
      "args": [
        "serve"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add biomcp -- biomcp serve

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

The client tool list should show biomcp tools such as search, get, and study; you can also run `biomcp health --apis-only` first to check API connectivity, then ask the client "What is the ClinVar significance of BRAF V600E?" to confirm live responses.

Troubleshooting

  1. Check `biomcp health` to verify API connectivity
  2. Ensure `biomcp` is on your PATH or use full path
  3. If using Docker, ensure container port mappings are correct
  4. For remote server, check `--allowed-hosts` restrictions
  5. Refer to official docs <https://biomcp.org/> and GitHub Issues

Things to try

Once connected, you can ask your AI assistant things like:

  • Search for articles about BRAF and melanoma, show the top 5.
  • Summarize ClinVar significance and population frequency for BRAF V600E.
  • Show drug interactions for pembrolizumab and find related trials.
  • Query mutations for TP53 in my local msk_impact_2017 study and draw a bar chart.

Tools 11

search read-only
Search entities (articles, variants, trials, etc.) across multiple sources.
get read-only
Fetch detailed information for a specific entity, with optional sections.
skill read-only
List and install guided investigation workflows.
discover read-only
Resolve concepts to aid entity selection.
enrich read-only
Perform gene-set enrichment using g:Profiler.
batch read-only
Parallel get calls for up to 10 focused entities.
study read-only
Perform query, cohort, survival, comparison, and co-occurrence analysis on local cBioPortal-style datasets.
health read-only
Check API connectivity and local resource readiness.
Show 3 more tools
version read-only
Show version and build info.
update writes
Self-update with checksum verification.
uninstall destructive
Remove biomcp from ~/.local/bin.

Use cases

Get a low-noise overview of BRAF in melanoma (e.g., `biomcp search all --gene BRAF --disease melanoma`).
Retrieve ClinVar significance and population frequency for BRAF V600E (`biomcp get variant "BRAF V600E" clinvar population`).
Perform study-level analysis on local datasets, such as survival analysis (`biomcp study ...`).
Expand literature evidence map via article citations, references, and recommendations.

Supported clients

Claude Desktop
Claude Code
Codex
Other MCP stdio clients

Listed from the project's documentation, not tested by this site.

Overview

BioMCP is a CLI tool that provides a single command grammar to access ~30 trusted biomedical sources (PubMed, ClinVar, ClinicalTrials.gov, OncoKB, Reactome, and more). It is also an MCP (Model Context Protocol) server, making the same tools available to AI agents such as Claude Code, Codex, and Claude Desktop. BioMCP simplifies the biomedical data maze by letting one query reach sources that normally live behind different APIs, identifiers, and search habits. Researchers, clinicians, and agents use the same command grammar to search, focus, and pivot without rebuilding workflows for each source. It returns compact, evidence-oriented results across live public data plus local study analytics.

Similar servers

Compare with other MCP servers

Source revision 7c1faf778c8f Data synced 2026-10-11 Read the FMRS scoring method