Deploy and operate the BioMCP server so MCP-compatible clients (Claude Desktop, LobeChat, etc.) can query biomedical databases via a single standardized interface.
When to Use
Unified literature search (PubMed/PMC) inside MCP clients.
Entity normalization via PubTator3 or genomic variant lookups.
ClinicalTrials.gov queries without bespoke API wrappers.
Core Capabilities
PubMed/PMC search: Execute complex literature queries.
PubTator3 annotations: Map text to genes, diseases, chemicals, species.
Run server:python -m biomcp.server or make run; Docker Compose provided.
Configure client: Add command/args snippet from README.md into MCP client config (Claude Desktop, BioKernel, etc.).
Test tools: Invoke PubMed + ClinicalTrials + variant endpoints to ensure connectivity.
Monitor: Capture logs, rate-limit statuses, and data-source versions for audit.
Guardrails
Keep API keys/env secrets outside the repo.
Respect upstream rate limits to avoid throttling or bans.
Document which data sources are enabled per deployment and update when they change.
References
Source repo + configuration examples in README.md, repo/docker-compose.yml, and repo/Makefile.
1---2name: biomcp-server3description: MCP bio bridge4license: MIT5---67<!--8# COPYRIGHT NOTICE9# This file is part of the "Universal Biomedical Skills" project.10# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>11# All Rights Reserved.12#13# This code is proprietary and confidential.14# Unauthorized copying of this file, via any medium is strictly prohibited.15#16# Provenance: Authenticated by MD BABU MIA1718-->192021# BioMCP Server2223Deploy and operate the BioMCP server so MCP-compatible clients (Claude Desktop, LobeChat, etc.) can query biomedical databases via a single standardized interface.2425## When to Use26- Unified literature search (PubMed/PMC) inside MCP clients.27- Entity normalization via PubTator3 or genomic variant lookups.28- ClinicalTrials.gov queries without bespoke API wrappers.2930## Core Capabilities311. **PubMed/PMC search:** Execute complex literature queries.322. **PubTator3 annotations:** Map text to genes, diseases, chemicals, species.333. **ClinicalTrials.gov:** Retrieve trial metadata/protocols.344. **Genomic variant lookups:** Fetch variant/gene summaries from connected sources.3536## Deployment Workflow371. **Install deps:** `cd repo && uv sync` (preferred) or `pip install .`.382. **Run server:** `python -m biomcp.server` or `make run`; Docker Compose provided.393. **Configure client:** Add command/args snippet from `README.md` into MCP client config (Claude Desktop, BioKernel, etc.).404. **Test tools:** Invoke PubMed + ClinicalTrials + variant endpoints to ensure connectivity.415. **Monitor:** Capture logs, rate-limit statuses, and data-source versions for audit.4243## Guardrails44- Keep API keys/env secrets outside the repo.45- Respect upstream rate limits to avoid throttling or bans.46- Document which data sources are enabled per deployment and update when they change.4748## References49- Source repo + configuration examples in `README.md`, `repo/docker-compose.yml`, and `repo/Makefile`.505152<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->
Run npx skillmds@latest add fridrichmethod/biomcp-server in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
MCP bio bridge It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.
FridrichMethod (@fridrichmethod) published this skill. Their other Agent Skills are listed on their SkillMD profile.
FridrichMethod