sample-agentic-ai-demos
Verified Safeby aws-samples
Overview
Provides various examples for building Agentic AI with AWS Bedrock using the Model Context Protocol (MCP) for tool invocation and inter-agent communication.
Installation
uv run modules/strands-mcp-inter-agent/employee-server/server.pyEnvironment Variables
- AWS_ACCESS_KEY_ID
- AWS_SECRET_ACCESS_KEY
- AWS_REGION
- BEDROCK_MODEL_ID
- EMPLOYEE_AGENT_URL
- EMPLOYEE_INFO_URL
- SERVER_URL
- AWS_BEARER_TOKEN_BEDROCK
- COGNITO_CLIENT_ID
- COGNITO_CLIENT_SECRET
- OAUTH_ENDPOINT
- EMPLOYEE_INFO_ARN
- EMPLOYEE_AGENT_ARN
- PORT
- PROJECT_NAME
- NODE_ENV
Security Notes
No obvious 'eval' usage, code obfuscation, or hardcoded sensitive secrets were found in the provided source code. Environment variables are consistently used for configuration and credentials (e.g., AWS API keys, region, model IDs), which is good practice. The tool definitions are structured and appear to handle inputs without allowing arbitrary code execution, mitigating common injection risks. External AWS SDKs and well-established frameworks like FastAPI and Spring AI are utilized, generally promoting secure development. However, as with any complex system, residual risks related to third-party dependencies or specific deployment configurations might exist.
Similar Servers
mcp-servers
A curated collection of Model Context Protocol (MCP) server configurations to integrate various developer tools and services with AI agents.
mcp-dotnet-samples
This MCP server retrieves GitHub Copilot customizations, including instructions, agents, prompts, and collections, from the `awesome-copilot` repository to provide contextual guidance to AI models.
Polymcp
A comprehensive TypeScript framework for building and orchestrating Model Context Protocol (MCP) servers and AI agents, enabling LLMs to intelligently discover, select, and execute external tools.
mcpc
Build and compose agentic Model Context Protocol (MCP) servers and tools, enabling AI assistants to discover, integrate, and orchestrate other MCP servers for complex tasks.