This project demonstrates how to use AWS Bedrock with Anthropic Claude and Amazon Nova models to create a web automation assistant with tool use, human-in-the-loop interaction, and vision capabilities.

Copilot Kit + AgentFramework + AG-UI + MCP

This pattern describes how to implement a Model Context Protocol (MCP) server that integrates three industry-standard security scanning tools (Checkov, Semgrep, and Bandit) to provide comprehensive code security analysis. The server enables AI coding assistants like Kiro and Amazon Q Developer to automatically scan code snippets.

Provide a simple and minimal MCP server implementation to help developers get started quickly with the Model Context Protocol. Enable basic MCP server capabilities using the official Python SDK as a foundation. Facilitate easy deployment and experimentation with MCP features.

Provide a Python-based MCP server implementation to enable integration of LLMs with external tools and resources. Facilitate dynamic interaction with data and actions through a standardized protocol. Simplify building MCP-compliant servers with Python tooling and CLI support.

Sample implementations of AI Agents and MCP Servers running on AWS Serverless compute

Access family personality profiles, relationship reports, and relational patterns via AI.

Graph-vector database that queried 1 billion edges for $2.50. Rust, OpenCypher, vector search, 14 graph algorithms. 74M nodes / 1B edges on a single machine.

Sana MCP server for trips, inventory, and packing readiness workflows.

Your agent, your machine, your keys — an MCP server that adds encrypted state, approval gates, and a portable identity to any AI agent.

Credential vault for AI agents — encrypted storage, lease-based access, CRP support.

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.

A Model Context Protocol (MCP) server that enables LLMs to run ANY code safely in isolated Docker containers.

A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

Locate dog shelters within a specified radius in San Francisco using an easy-to-use API. Quickly find nearby shelters by providing a location and radius. Simplify your search for dog shelters with this dedicated tool.

Deprecated: Use the remote MCP server at https://mcp.sanity.io instead.

Search official documentation for well-known libraries.