iSharkFly-Docs/amazon-bedrock-agentcore-samples
1
0
Fork 0
mirror of https://github.com/awslabs/amazon-bedrock-agentcore-samples.git synced 2025-09-08 20:50:46 +00:00
Code Issues Packages Projects Releases Wiki Activity
amazon-bedrock-agentcore-sa.../02-use-cases/SRE-agent/gateway
History
Amit Arora a6fc665364 feat: Add debug mode support and comprehensive deployment guide 
Add --debug command line flag and DEBUG environment variable support:
- Created shared logging configuration module
- Updated CLI and runtime to support --debug flag
- Made debug traces conditional on DEBUG environment variable
- Added debug mode for container and AgentCore deployments

Enhanced build and deployment script:
- Added command line argument for ECR repository name
- Added help documentation and usage examples
- Added support for local builds (x86_64) vs AgentCore builds (arm64)
- Added environment variable pass-through for DEBUG, LLM_PROVIDER, ANTHROPIC_API_KEY

Created comprehensive deployment guide:
- Step-by-step instructions from local testing to production
- Docker platform documentation (x86_64 vs arm64)
- Environment variable configuration with .env file usage
- Debug mode examples and troubleshooting guide
- Provider configuration for Bedrock and Anthropic

Updated README with AgentCore Runtime deployment section and documentation links.
2025-07-25 21:59:13 +00:00
..
.env.example
renaming folders (#102)
2025-07-21 10:45:13 -04:00
config.yaml.example
renaming folders (#102)
2025-07-21 10:45:13 -04:00
create_credentials_provider.py
renaming folders (#102)
2025-07-21 10:45:13 -04:00
create_gateway.sh
renaming folders (#102)
2025-07-21 10:45:13 -04:00
generate_token.py
renaming folders (#102)
2025-07-21 10:45:13 -04:00
generate_token.sh
renaming folders (#102)
2025-07-21 10:45:13 -04:00
main.py
feat: Add debug mode support and comprehensive deployment guide
2025-07-25 21:59:13 +00:00
mcp_cmds.sh
renaming folders (#102)
2025-07-21 10:45:13 -04:00
observability.py
renaming folders (#102)
2025-07-21 10:45:13 -04:00
README.md
renaming folders (#102)
2025-07-21 10:45:13 -04:00

README.md

Gateway Component

This directory contains the MCP (Model Context Protocol) gateway management tools for SRE Agent.

📁 Files

  • main.py - AgentCore Gateway Management Tool for creating and managing AWS AgentCore Gateways
  • mcp_cmds.sh - Shell script for MCP gateway operations and setup
  • generate_token.py - JWT token generation for gateway authentication
  • openapi_s3_target_cognito.sh - Script for adding OpenAPI targets with S3 and Cognito integration
  • config.yaml - Gateway configuration file
  • config.yaml.example - Example configuration template
  • .env - Environment variables for gateway setup
  • .env.example - Example environment variables template

🚀 Gateway Setup

Step-by-Step Setup

  1. Configure the gateway (copy and edit config):

    cd gateway
cp config.yaml.example config.yaml
cp .env.example .env
# Edit config.yaml and .env with your specific settings

  2. Create the gateway:

    ./create_gateway.sh

  3. Test the gateway:

    ./mcp_cmds.sh

# To capture output to a log file for debugging:
./mcp_cmds.sh 2>&1 | tee mcp_cmds.log

This setup process will:

  • Configure the MCP gateway infrastructure
  • Create the gateway with proper authentication and token management
  • Test the gateway functionality and validate the setup

🔧 Components

Gateway Management (main.py)

The main gateway management tool provides functionality to:

  • Create and manage AWS AgentCore Gateways
  • Support MCP protocol integration
  • Handle JWT authorization
  • Add OpenAPI targets from S3 or inline schemas

MCP Commands (mcp_cmds.sh)

Shell script that orchestrates the gateway setup process including:

  • Gateway creation
  • Configuration validation
  • Service registration
  • Health checking

Token Generation (generate_token.py)

Utility for generating JWT tokens for gateway authentication:

python generate_token.py --config config.yaml

OpenAPI Integration (openapi_s3_target_cognito.sh)

Script for integrating OpenAPI specifications with S3 storage and Cognito authentication.

🔍 Usage

Quick Reference

  1. Configure your settings in config.yaml
  2. Create the gateway: ./create_gateway.sh
  3. Test the gateway: ./mcp_cmds.sh
  4. For debugging, capture output: ./mcp_cmds.sh 2>&1 | tee mcp_cmds.log
  5. Verify gateway is running and accessible
  6. Generate tokens as needed for client authentication

Development Mode

For development and testing, you can also run components individually:

# Generate tokens
python generate_token.py

# Create gateway with specific config
python main.py --config config.yaml

# Add OpenAPI targets
./openapi_s3_target_cognito.sh

⚠️ Important Notes

  • Always run mcp_cmds.sh from the gateway directory
  • Ensure config.yaml is properly configured before setup
  • The gateway must be running before starting SRE Agent investigations
  • Keep authentication tokens secure and rotate them regularly
  • Log files (*.log) are automatically ignored by git - safe to create for debugging

🔗 Integration

Once the gateway is set up and running, it provides the MCP endpoint that the SRE Agent core system connects to for accessing infrastructure APIs and tools.