hcls-deploy-agent
Skill274 starsChanged 6 months agoMIT-0View on GitHub
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.
- Installs packages
In this repository9 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 43
Run the prerequisite script (creates Lambda tools, Cognito, Gateway):
- Distinctive: line 105
When deploying, the following AWS MCP servers help:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Deploying an HCLS Agent
When to use this skill
- Developer asks "how do I deploy this agent?"
- Developer needs to configure AgentCore Gateway, Runtime, Memory, or Identity
- Developer wants to expose tools as MCP endpoints
- Developer wants to register an agent in the AgentCore Registry
Deployment Components
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 workflowsSteps
1. Prerequisites
# Install AgentCore CLI
pip install bedrock-agentcore
# Configure
agentcore configure --entrypoint main.py \
-rf agent/requirements.txt \
-er <IAM_ROLE_ARN> \
--name <agent-name>2. Deploy Infrastructure
Run the prerequisite script (creates Lambda tools, Cognito, Gateway):
./scripts/prereq.shThis deploys CloudFormation stacks for:
- Lambda functions (tool handlers)
- IAM roles (agent execution, Gateway invocation)
- Cognito user pool (OAuth2 authentication)
- AgentCore Gateway (MCP endpoint with tool targets)
- AgentCore Memory (conversation persistence)
3. Deploy Agent Runtime
# Remove stale config
rm -f .agentcore.yaml
# Launch (builds container, pushes to ECR, deploys to Runtime)
agentcore launch4. Verify
# 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-conversation5. Register in AgentCore Registry (optional)
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={...}
)Deployment Templates
| Template | What it deploys |
agentcore_template/ | Backend: Runtime + Gateway + Memory + Streamlit UI |
| FAST | Full-stack: React/Amplify + Cognito + AgentCore + CDK |
AWS MCP Servers Used
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 code
References
- Deployment scripts:
agentcore_template/scripts/ - Full deployment example:
agents_catalog/28-Research-agent-biomni-gateway-tools/scripts/prereq.sh - FAST template deployment:
agents_catalog/35-Terminology-agent/
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

