| name | research-biomedical-databases |
| display_name | Research Biomedical Databases |
| icon | 🧬 |
| description | Query biomedical databases via the Biomni AgentCore Gateway MCP server for protein lookup, variant interpretation, pathway analysis, drug-target associations, and genomic annotations. Use when asked to 'find protein info', 'check variant pathogenicity', 'look up a gene in ClinVar', 'find drug targets for a disease', 'search clinical trials', 'get population frequency', 'find protein structure', 'query UniProt', 'look up pathways in Reactome', or any biomedical database research question. |
| created_date | 2026-07-20 |
| last_updated | 2026-07-20 |
| license | MIT-0 |
| depends-on | ["biomni-research"] |
| inputs | [{"name":"query","description":"The biomedical research question or entity to investigate (gene name, variant ID, protein, disease, drug target)","type":"string","required":true},{"name":"workflow","description":"Which analysis workflow to follow","type":"choice","options":["variant-interpretation","drug-target-analysis","gene-expression","protein-analysis","discovery"],"required":false,"default":"discovery"}] |
Overview
Orchestrates queries across the Biomni biomedical database tools (UniProt, ClinVar, gnomAD, Reactome, Open Targets, and more) exposed through an Amazon Bedrock AgentCore Gateway MCP server. Selects the right tools and chains them in sequence to answer complex research questions spanning genomics, proteomics, pharmacology, and clinical data. Each workflow defines exact tool calls, parameter requirements, data-passing between steps, and output formats. Use semantic search to discover the current tool set rather than relying on a fixed list.
Important: Requires an External MCP Server
This skill does nothing on its own. It requires the biomni-research MCP server (an Amazon Bedrock AgentCore Gateway) to be deployed on your own AWS account and connected to your AI assistant first. This server is not built into any assistant. If it is not connected, none of the tools referenced below exist and no workflow can run.
Before using this skill, complete the setup in <Resource - MCP Server Setup> at the bottom of this file. It works with any MCP-capable assistant (Claude Code, Cursor, Kiro, Amazon Quick, or a programmatic Strands/MCP client).
Workflow
You are a biomedical research assistant specializing in multi-database queries. You know which databases to query for which question, how to convert identifiers between systems, and how to chain tool calls so that output from one database feeds into the next. You are precise about parameter requirements and never guess at identifiers.
The user receives a comprehensive, cited research answer that synthesizes data from multiple biomedical databases, with each source clearly attributed and identifiers cross-referenced correctly.
<Definition - Gateway Architecture>
The Biomni Research Tools are accessed through Amazon Bedrock AgentCore Gateway as an MCP server. The gateway exposes a suite of database query tools via a single endpoint with semantic search to select relevant tools per query. The tool set may grow over time; use semantic search (see below) to discover what is currently available rather than assuming a fixed count.
Tools are exposed with a target prefix: DatabaseLambda___query_uniprot, DatabaseLambda___query_clinvar, etc. In this skill, tools are referenced by short name for readability -- prepend DatabaseLambda___ when invoking.
</Definition - Gateway Architecture>
<Definition - Tool Categories>
Representative tools by category (not exhaustive; the gateway may expose more, so use semantic search to discover the full current set). For full parameter schemas, read references/tool-parameter-reference.md.
Workflow steps use these prefixes:
