AWS Bedrock AgentCore
When to Use
Use this skill when you need aWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations. Covers agent deployment, MCP...
AWS Bedrock AgentCore provides a complete platform for deploying and scaling AI agents with nine core services. This skill covers service selection, deployment patterns, and integration workflows using AWS CLI.
How to use this skill: Identify the service(s) the user needs from the table below, then read the corresponding service README before responding. For cross-service patterns (credentials, security, registry integration), check the Cross-Service Resources section. Verify AWS-specific details using the MCP documentation tools.
AWS Documentation Requirement
Always verify AWS facts using MCP tools before answering. Two documentation sources are available:
- AgentCore-specific docs (
mcp__acdocs__*) — bundled with this plugin, provides search_agentcore_docs and fetch_agentcore_doc for AgentCore documentation
- General AWS docs (
mcp__aws-mcp__* or mcp__*awsdocs*__*) — loaded via the aws-mcp-setup dependency for broader AWS documentation
Prefer the AgentCore docs MCP for AgentCore-specific questions. If MCP tools are unavailable, guide the user through the aws-mcp-setup skill's setup flow.
Available Services
Common Workflows
Deploying a Gateway Target
Read services/gateway/README.md before implementing — Gateway setup involves deployment strategies, IAM, and auth choices that vary significantly by use case.
- Upload OpenAPI schema to S3
- (API Key auth only) Create credential provider and store API key
- Create gateway target linking schema (and credentials if using API key)
- Verify target status and test connectivity
Credential provider is only needed for API key authentication. Lambda targets use IAM roles, and MCP servers use OAuth.
Managing Credentials
Read cross-service/credential-management.md first — credential patterns differ across services and getting them wrong causes hard-to-debug auth failures.
- Use Identity service credential providers for all API keys
- Link providers to gateway targets via ARN references
- Rotate credentials quarterly through credential provider updates
- Monitor usage with CloudWatch metrics
Discovering Agents and Tools (Agent Registry)
Read services/registry/README.md first — the registry has governance workflows, MCP endpoint options, and sync modes that affect how records become discoverable.
- Create a registry to catalog your organization's AI resources
- Register resources (MCP servers, agents, skills, custom) with descriptive metadata
- Submit records for approval (auto-approve for dev, manual for production)
- Search and discover approved resources via CLI or MCP endpoint
Agent Registry is in Preview. Available in us-east-1, us-west-2, eu-west-1, ap-northeast-1, ap-southeast-2.
Evaluating Agent Quality
Read services/evaluations/README.md first — evaluators, scoring modes, and IAM setup vary between online monitoring and on-demand testing.
- Instrument the agent with OpenTelemetry (ADOT) for trace collection
- Create evaluators (use built-in like
Builtin.Helpfulness or create custom)
- Set up online evaluation with sampling rate and data source
- Monitor scores in CloudWatch dashboards; investigate low-scoring sessions
Monitoring Agents
Read services/observability/README.md for the full monitoring setup — observability configuration depends on your Runtime protocol and framework choice.
- Enable observability for agents
- Configure CloudWatch dashboards for metrics
- Set up alarms for error rates and latency
- Use X-Ray for distributed tracing
Deep-Dive References
Each service README (linked in the table above) contains sub-links to getting-started guides, troubleshooting, and advanced topics. Start with the service README and follow pointers from there.
Advanced Runtime & OAuth References
Deep-dive reference documentation for Runtime internals, deployment, OAuth integration, and communication protocols. Read these when building production Runtime deployments or configuring OAuth authentication:
- OAuth Integration:
references/agentcore-oauth-integration.md - Three-layer OAuth architecture (Inbound JWT, Outbound Credential Provider, Gateway OAuth), Cognito configuration, supported IdPs, end-to-end CDK examples
- Runtime Core Mechanisms:
references/agentcore-runtime-core.md - Container contract, MicroVM Session model, Agent lifecycle (per-request vs per-session), tool integration (MCP/HTTP), startup flow
- Runtime Deployment & Operations:
references/agentcore-runtime-deploy.md - CDK deployment (L1/L2 constructs), multi-Runtime architecture, security model, observability (OTel/CloudWatch), BedrockAgentCoreApp vs FastAPI comparison
- Runtime Protocol Reference:
references/agentcore-runtime-protocols.md - HTTP, MCP, A2A, AG-UI protocol specifications with container contracts, endpoint specs, and selection guide
Runnable Script Templates
Production-ready templates in scripts/ for common deployment patterns:
Cross-Service Resources
For patterns and best practices that span multiple AgentCore services:
Additional Resources
Example
User request:
Use @aws-agentic-ai for this task: AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale.
Limitations
- Use this skill only when the task clearly matches its upstream source and local project context.
- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.
1---2name: aws-agentic-ai3description: "AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations."4risk: critical5source: https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai6source_repo: zxkane/aws-skills7source_type: community8date_added: 2026-07-019license: MIT10license_source: https://github.com/zxkane/aws-skills/blob/main/LICENSE11metadata:12 source: https://skillmd.com/skills/zxkane/aws-agentic-ai13---1415# AWS Bedrock AgentCore16## When to Use1718Use this skill when you need aWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations. Covers agent deployment, MCP...192021AWS Bedrock AgentCore provides a complete platform for deploying and scaling AI agents with nine core services. This skill covers service selection, deployment patterns, and integration workflows using AWS CLI.2223**How to use this skill**: Identify the service(s) the user needs from the table below, then read the corresponding service README before responding. For cross-service patterns (credentials, security, registry integration), check the Cross-Service Resources section. Verify AWS-specific details using the MCP documentation tools.2425## AWS Documentation Requirement2627Always verify AWS facts using MCP tools before answering. Two documentation sources are available:28- **AgentCore-specific docs** (`mcp__acdocs__*`) — bundled with this plugin, provides `search_agentcore_docs` and `fetch_agentcore_doc` for AgentCore documentation29- **General AWS docs** (`mcp__aws-mcp__*` or `mcp__*awsdocs*__*`) — loaded via the `aws-mcp-setup` dependency for broader AWS documentation3031Prefer the AgentCore docs MCP for AgentCore-specific questions. If MCP tools are unavailable, guide the user through the `aws-mcp-setup` skill's setup flow.3233## Available Services3435| Service | Use For | Documentation |36|---------|---------|---------------|37| **Gateway** | Converting REST APIs to MCP tools | [`services/gateway/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/gateway/README.md) |38| **Runtime** | Deploying and scaling agents | [`services/runtime/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/runtime/README.md) |39| **Memory** | Managing conversation state | [`services/memory/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/memory/README.md) |40| **Identity** | Credential and access management | [`services/identity/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/identity/README.md) |41| **Code Interpreter** | Secure code execution in sandboxes | [`services/code-interpreter/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/code-interpreter/README.md) |42| **Browser** | Web automation and scraping | [`services/browser/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/browser/README.md) |43| **Observability** | Tracing and monitoring | [`services/observability/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/observability/README.md) |44| **Agent Registry** | Catalog, discover, and govern agents/tools (Preview) | [`services/registry/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/registry/README.md) |45| **Evaluations** | Automated agent quality assessment (LLM-as-a-Judge) | [`services/evaluations/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/evaluations/README.md) |4647## Common Workflows4849### Deploying a Gateway Target5051Read [`services/gateway/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/gateway/README.md) before implementing — Gateway setup involves deployment strategies, IAM, and auth choices that vary significantly by use case.52531. Upload OpenAPI schema to S3542. *(API Key auth only)* Create credential provider and store API key553. Create gateway target linking schema (and credentials if using API key)564. Verify target status and test connectivity5758> Credential provider is only needed for API key authentication. Lambda targets use IAM roles, and MCP servers use OAuth.5960### Managing Credentials6162Read [`cross-service/credential-management.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/cross-service/credential-management.md) first — credential patterns differ across services and getting them wrong causes hard-to-debug auth failures.63641. Use Identity service credential providers for all API keys652. Link providers to gateway targets via ARN references663. Rotate credentials quarterly through credential provider updates674. Monitor usage with CloudWatch metrics6869### Discovering Agents and Tools (Agent Registry)7071Read [`services/registry/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/registry/README.md) first — the registry has governance workflows, MCP endpoint options, and sync modes that affect how records become discoverable.72731. Create a registry to catalog your organization's AI resources742. Register resources (MCP servers, agents, skills, custom) with descriptive metadata753. Submit records for approval (auto-approve for dev, manual for production)764. Search and discover approved resources via CLI or MCP endpoint7778> Agent Registry is in Preview. Available in us-east-1, us-west-2, eu-west-1, ap-northeast-1, ap-southeast-2.7980### Evaluating Agent Quality8182Read [`services/evaluations/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/evaluations/README.md) first — evaluators, scoring modes, and IAM setup vary between online monitoring and on-demand testing.83841. Instrument the agent with OpenTelemetry (ADOT) for trace collection852. Create evaluators (use built-in like `Builtin.Helpfulness` or create custom)863. Set up online evaluation with sampling rate and data source874. Monitor scores in CloudWatch dashboards; investigate low-scoring sessions8889### Monitoring Agents9091Read [`services/observability/README.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/services/observability/README.md) for the full monitoring setup — observability configuration depends on your Runtime protocol and framework choice.92931. Enable observability for agents942. Configure CloudWatch dashboards for metrics953. Set up alarms for error rates and latency964. Use X-Ray for distributed tracing9798## Deep-Dive References99100Each service README (linked in the table above) contains sub-links to getting-started guides, troubleshooting, and advanced topics. Start with the service README and follow pointers from there.101102### Advanced Runtime & OAuth References103104Deep-dive reference documentation for Runtime internals, deployment, OAuth integration, and communication protocols. Read these when building production Runtime deployments or configuring OAuth authentication:105106- **OAuth Integration**: [`references/agentcore-oauth-integration.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/references/agentcore-oauth-integration.md) - Three-layer OAuth architecture (Inbound JWT, Outbound Credential Provider, Gateway OAuth), Cognito configuration, supported IdPs, end-to-end CDK examples107- **Runtime Core Mechanisms**: [`references/agentcore-runtime-core.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/references/agentcore-runtime-core.md) - Container contract, MicroVM Session model, Agent lifecycle (per-request vs per-session), tool integration (MCP/HTTP), startup flow108- **Runtime Deployment & Operations**: [`references/agentcore-runtime-deploy.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/references/agentcore-runtime-deploy.md) - CDK deployment (L1/L2 constructs), multi-Runtime architecture, security model, observability (OTel/CloudWatch), BedrockAgentCoreApp vs FastAPI comparison109- **Runtime Protocol Reference**: [`references/agentcore-runtime-protocols.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/references/agentcore-runtime-protocols.md) - HTTP, MCP, A2A, AG-UI protocol specifications with container contracts, endpoint specs, and selection guide110111### Runnable Script Templates112113Production-ready templates in [`scripts/`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/scripts/) for common deployment patterns:114115| Script | Protocol | Description |116|--------|----------|-------------|117| [`Dockerfile.runtime-template`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/scripts/Dockerfile.runtime-template) | — | ARM64 multi-stage Docker build for AgentCore Runtime |118| [`runtime-fastapi-template.py`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/scripts/runtime-fastapi-template.py) | HTTP | FastAPI Runtime with SSE streaming and MCPClient |119| [`mcp-server-template.py`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/scripts/mcp-server-template.py) | MCP | MCP Server with Streamable HTTP transport |120| [`a2a-server-template.py`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/scripts/a2a-server-template.py) | A2A | A2A Server with Agent Card discovery |121| [`agui-server-template.py`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/scripts/agui-server-template.py) | AG-UI | AG-UI Server with standard AG-UI event stream |122| [`gateway-custom-resource-lambda.py`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/scripts/gateway-custom-resource-lambda.py) | — | CDK Custom Resource Lambda for Gateway lifecycle |123124## Cross-Service Resources125126For patterns and best practices that span multiple AgentCore services:127128- **Credential Management**: [`cross-service/credential-management.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/cross-service/credential-management.md) - Unified credential patterns, security practices, rotation procedures129- **Registry Integration**: [`cross-service/registry-integration.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/cross-service/registry-integration.md) - Cross-service patterns with Gateway, Identity, Runtime130- **Security & Resource Policies**: [`cross-service/security-resource-policies.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/cross-service/security-resource-policies.md) - Resource-based policies, cross-account access, VPC/IP restrictions131- **Agent Deployment with S3 Files**: [`cross-service/agent-persistence-patterns.md`](https://github.com/zxkane/aws-skills/tree/main/plugins/aws-agentic-ai/skills/aws-agentic-ai/cross-service/agent-persistence-patterns.md) - Deploy Strands Agents, OpenClaw, Claude Agent SDK on AgentCore with S3 Files and Session Storage132133## Additional Resources134135- **AWS Documentation**: [Amazon Bedrock AgentCore](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html)136- **API Reference**: [Bedrock AgentCore Control Plane API](https://docs.aws.amazon.com/bedrock-agentcore-control/latest/APIReference/)137- **AWS CLI Reference**: [bedrock-agentcore-control commands](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/bedrock-agentcore-control/index.html)138139## Example140141**User request:**142143> Use @aws-agentic-ai for this task: AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale.144145## Limitations146147- Use this skill only when the task clearly matches its upstream source and local project context.148- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.149- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.