medical-research-toolkit

Query 14+ biomedical databases for drug repurposing, target discovery, and clinical evidence research.

1|Updated Jul 13, 2026
One-click install
npx skills add https://github.com/HalseyYang/Skills-HY --skill medical-research-toolkit-halseyyang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: medical-research-toolkit
Source: https://github.com/HalseyYang/Skills-HY/tree/main/medical-research-toolkit
Command: npx skills add https://github.com/HalseyYang/Skills-HY --skill medical-research-toolkit-halseyyang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Biomedical research requires querying many separate databases (PubMed, ChEMBL, ClinicalTrials.gov, OpenTargets, OpenFDA, OMIM) with different APIs and ID formats, making drug repurposing and target discovery workflows slow and fragmented. ## Core Features & Use Cases - Unified MCP Endpoint: Access 14+ biomedical databases through one JSON-RPC endpoint with copy-paste curl commands and no setup required. - Complete Database Guides: Detailed references for PubMed, ClinicalTrials.gov, ChEMBL, OpenTargets, OpenFDA, OMIM, plus Reactome, UniProt, KEGG, GWAS, and ID-mapping services. - End-to-End Workflows: An 8-step drug repurposing pipeline covering target identification, drug screening, trial search, literature review, and safety assessment. - Use Case: Find repurposing candidates for myasthenia gravis by pulling disease targets from OpenTargets, matching drugs in ChEMBL, checking recruiting trials, and reviewing FDA adverse events. ## Quick Start Ask the agent to find approved and investigational drugs for myasthenia gravis using the ChEMBL indication search via the unified MCP endpoint.

Frequently Asked Questions about medical-research-toolkit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find drugs for a disease using ChEMBL?

Call chembl_find_drugs_by_indication with the disease name and max_results via the unified MCP endpoint. It returns approved and investigational drugs with their maximum clinical phase reached.

How to find therapeutic targets for a disease with OpenTargets?

First call opentargets_search with the disease name to get its disease ID, then call opentargets_get_associations with that ID. Results return targets ranked by evidence strength on a 0-1 score.

Do these biomedical APIs require API keys?

Most databases are free with no key required, including ChEMBL, PubMed, OpenTargets, and ClinicalTrials.gov. OMIM requires a key from omim.org, while OpenFDA and NCI Clinical Trials offer optional keys for higher rate limits.

Can I search clinical trials by phase and recruitment status?

Yes, ctg_search_studies accepts condition, intervention, phase (PHASE1 through PHASE4), and recruitment_status filters such as RECRUITING. It returns trials with NCT IDs, titles, and enrollment details.

Why does my OpenTargets query return no results?

OpenTargets uses specific disease ID formats such as EFO or MONDO identifiers rather than free text for association queries. Search first with opentargets_search to resolve the correct ID, and try alternative gene symbols or disease synonyms.

How do I convert gene IDs between different databases?

Use the nodenorm_get_normalized_nodes tool with a CURIE identifier like HGNC:11998. It returns equivalent IDs across NCBI Gene, UniProt, Ensembl, and MyGene for cross-database workflows.