// Use when a developer wants to deploy an HCLS agent to Amazon Bedrock AgentCore, configure Gateway tools as MCP endpoints, set up authentication with Cognito, configure memory, or register an agent in the AgentCore Registry. Also use for deployment troubleshooting.
Use when a researcher needs to query biomedical databases for biomarker discovery, build target profiles from UniProt/Open Targets/STRING, rank biomarker candidates by evidence strength, or generate SQL queries against clinical genomic databases.
Use when orchestrating a multi-agent biomarker discovery workflow that requires coordinating database queries, pathway analysis, literature review, statistical modeling, and clinical evidence synthesis to produce ranked biomarker panels.
Use when a researcher needs to analyze biological pathways for biomarker discovery, map disease mechanisms to druggable targets using Reactome/KEGG, identify pathway enrichment from gene sets, or understand mechanism-of-action for candidate biomarkers.
Use when interpreting genomic variants from VCF files, performing clinical variant classification using ClinVar/VEP annotations, analyzing allele frequencies against population data (1000 Genomes), or generating clinical reports for genetic counseling.
Use when a developer wants to build a new healthcare or life sciences agent, structure tools and system prompts for an HCLS workflow, or create a Strands agent with domain-specific capabilities. Also use when someone asks about agent architecture, tool design, or system prompt patterns for clinical, genomics, or drug discovery use cases.
Use when a developer asks how to get started building healthcare or life sciences agents, wants to understand the HCLS Agents Toolkit, or asks what's available in this repository. Also use when someone asks about genomics, drug discovery, clinical trials, or biomarker agents on AWS.
| name | hcls-deploy-agent |
| description | Use when a developer wants to deploy an HCLS agent to Amazon Bedrock AgentCore, configure Gateway tools as MCP endpoints, set up authentication with Cognito, configure memory, or register an agent in the AgentCore Registry. Also use for deployment troubleshooting. |
AgentCore Deployment
├── Runtime — Hosts the agent container
├── Gateway — Exposes tools as MCP endpoints (Lambda targets)
├── Memory — Conversation persistence (semantic, summary, preferences)
├── Identity — Cognito OAuth2 authentication
└── Registry — Agent discovery for multi-agent workflows
# Install AgentCore CLI
pip install bedrock-agentcore
# Configure
agentcore configure --entrypoint main.py \
-rf agent/requirements.txt \
-er <IAM_ROLE_ARN> \
--name <agent-name>
Run the prerequisite script (creates Lambda tools, Cognito, Gateway):
./scripts/prereq.sh
This deploys CloudFormation stacks for:
# Remove stale config
rm -f .agentcore.yaml
# Launch (builds container, pushes to ECR, deploys to Runtime)
agentcore launch
# Invoke the deployed agent
agentcore invoke '{"prompt": "Hello, can you help me?"}'
# Test Gateway tools independently
python tests/test_gateway.py --prompt "Test query"
# Test memory
python tests/test_memory.py load-conversation
For multi-agent discovery, register the agent:
import boto3
client = boto3.client('bedrock-agentcore')
client.create_registry_record(
registryName="hcls-registry",
recordName="<agent-name>",
description="<rich description for semantic search>",
descriptorType="MCP", # or "A2A" for agent-to-agent
descriptors={...}
)
| Template | What it deploys |
|---|---|
agentcore_template/ | Backend: Runtime + Gateway + Memory + Streamlit UI |
| FAST | Full-stack: React/Amplify + Cognito + AgentCore + CDK |
When deploying, the following AWS MCP servers help:
agentcore-docs — API reference for Gateway/Runtime/Memory/Registryaws-mcp — create IAM roles, manage CloudFormation stacks, configure S3strands-docs — framework patterns for agent codeagentcore_template/scripts/agents_catalog/28-Research-agent-biomni-gateway-tools/scripts/prereq.shagents_catalog/35-Terminology-agent/