The MCP Tool Server allows interaction with Anthropic's Model Context Protocol on AWS Bedrock to fetch website content.
Fetch Website Content: Retrieves content from websites by providing a URL
AWS Bedrock Integration: Seamlessly integrates with AWS Bedrock's runtime using the Converse API
Tool Format Conversion: Converts tool formats to be compatible with AWS Bedrock
Asynchronous Communication: Handles asynchronous processing efficiently
Streamable HTTP Support: Offers efficient data streaming
Customizable Ports: Allows running the server on custom ports
Enables interaction with AWS Bedrock's runtime service to connect Claude AI models with MCP-enabled tools
MCP on AWS Bedrock
A simple and clear example for implementation and understanding Anthropic MCP (on AWS Bedrock).
For multiple MCP servers management, this tiny project Q-2001 could be referred~
Overview
This project demonstrates how to implement and use Anthropic's Model Context Protocol (MCP) with AWS Bedrock. It provides a client implementation that can interact with MCP-enabled tools through AWS Bedrock's runtime service.
Related MCP server: MCP SysOperator
Updates 2025-05-10: Streamable HTTP
Add support for Streamable HTTP
Rewrite the URL fetching MCP server
fetch_url_mcp_server.pythat demonstrates different transport types
Usage Instructions
Run the server with default stdio settings (no transport parameter):
Run with streamable-http transport on default port (8000):
Run with streamable-http transport on custom port:
Prerequisites
Python 3.10 or higher
AWS account with Bedrock access
Configured AWS credentials
UV package manager
Features
Seamless integration with AWS Bedrock runtime using Converse API
Tool format conversion for Bedrock compatibility
Asynchronous communication handling
Structured logging for debugging
Contributing
Feel free to submit issues and pull requests to improve the implementation.
License
MIT License