https://github.com/davidshtian/mcp-on-aws-bedrock
A simple and clear example for implementation and understanding Anthropic MCP (on AWS Bedrock).
https://github.com/davidshtian/mcp-on-aws-bedrock
Last synced: 3 months ago
JSON representation
A simple and clear example for implementation and understanding Anthropic MCP (on AWS Bedrock).
- Host: GitHub
- URL: https://github.com/davidshtian/mcp-on-aws-bedrock
- Owner: davidshtian
- License: mit
- Created: 2024-12-26T14:04:36.000Z (9 months ago)
- Default Branch: hand
- Last Pushed: 2025-05-10T05:16:22.000Z (5 months ago)
- Last Synced: 2025-05-10T06:21:35.495Z (5 months ago)
- Language: Python
- Homepage:
- Size: 17.6 KB
- Stars: 46
- Watchers: 2
- Forks: 9
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 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](https://github.com/davidshtian/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.
## Updates 2025-05-10: Streamable HTTP
- Add support for [Streamable HTTP](https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.8.0)
- Rewrite the URL fetching MCP server `fetch_url_mcp_server.py` that demonstrates different transport types
### Usage Instructions
Run the server with default stdio settings (no transport parameter):
```bash
uv run fetch_url_mcp_server.py
# client
uv run client_stdio.py
```
Run with streamable-http transport on default port (8000):
```bash
python fetch_url_mcp_server.py --transport streamable-http
# client
uv run client_streamablehttp.py
```
Run with streamable-http transport on custom port:
```bash
python fetch_url_mcp_server.py --transport streamable-http --port 8080
```
## 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
## References
- [Anthropic MCP](https://modelcontextprotocol.io/)
- [MCP Python SDK](https://github.com/modelcontextprotocol/python-sdk)
- [AWS Bedrock](https://aws.amazon.com/bedrock/)