
amazon-bedrock-mcp
Demo of Anthropic's open source MCP used with Amazon Bedrock Converse API
3 years
Works with Finder
5
Github Watches
22
Github Forks
81
Github Stars
Amazon Bedrock Converse API MCP Demo
This is a demo of Anthropic's open source MCP used with Amazon Bedrock Converse API. This combination allows for the MCP to be used with any of the many models supported by the Converse API.
Prerequisites
- Python 3.8+
- AWS account with Bedrock access
- AWS credentials configured locally
- SQLite database (Follow the instructions in the MCP Quick Start Guide to set this up.)
Installation
- Clone the repository:
git clone <repository-url>
cd <project-directory>
- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install required packages:
pip install -r requirements.txt
Configuration
- Ensure AWS credentials are properly configured in
~/.aws/credentials
or via environment variables:
export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key
export AWS_DEFAULT_REGION=us-west-2
- The default configuration uses:
- Model: anthropic.claude-3-5-sonnet-20241022-v2:0
- Region: us-west-2
- SQLite database path: ~/test.db
Project Structure
-
app.py
: Main application entry point and interactive loop -
converse_agent.py
: Core agent implementation with Bedrock integration -
converse_tools.py
: Tool management and execution system -
mcp_client.py
: MCP (Model Control Protocol) client implementation
Usage
- Start the application:
python app.py
- Enter prompts when prompted. The agent will:
- Process your input
- Execute any necessary tools
- Provide responses
- Maintain conversation context
- Exit the application by typing 'quit', 'exit', 'q', or using Ctrl+C
Key Components
ConverseAgent
The main agent class that:
- Manages conversation flow
- Integrates with Bedrock
- Handles tool execution
- Processes responses
Reference:
startLine: 3
endLine: 109
ConverseToolManager
Manages tool registration and execution:
- Tool registration with schemas
- Name sanitization
- Tool execution handling
Reference:
startLine: 5
endLine: 76
MCPClient
Handles communication with the MCP server:
- Tool discovery
- Tool execution
- Server connection management
Reference:
startLine: 6
endLine: 48
Security
See CONTRIBUTING for more information.
License
This library is licensed under the MIT-0 License. See the LICENSE file.
相关推荐
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Converts Figma frames into front-end code for various mobile frameworks.
Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.
Advanced software engineer GPT that excels through nailing the basics.
Delivers concise Python code and interprets non-English comments
💬 MaxKB is a ready-to-use AI chatbot that integrates Retrieval-Augmented Generation (RAG) pipelines, supports robust workflows, and provides advanced MCP tool-use capabilities.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
MCP server to provide Figma layout information to AI coding agents like Cursor
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Python code to use the MCP3008 analog to digital converter with a Raspberry Pi or BeagleBone black.
Reviews

user_DgLW4Kkh
I have been using amazon-bedrock-mcp for a while, and it has truly transformed my workflow. The integration and functionality provided by mikegc-aws are impressive. The documentation is thorough, and the support is outstanding. Highly recommend checking it out at https://github.com/mikegc-aws/amazon-bedrock-mcp.