AWS Bedrock Logs MCP Server
by dheerajoruganty
This tool provides a command-line interface and API for analyzing AWS Bedrock usage and logs through Anthropic's MCP. It functions as an MCP server that exposes AWS CloudWatch Logs API functionality to Claude, allowing you to query and analyze your Bedrock usage data in natural language.
Last updated: N/A
What is AWS Bedrock Logs MCP Server?
This is an MCP server that allows you to analyze AWS Bedrock model invocation logs using Anthropic's Claude model as an interactive interface. It exposes AWS CloudWatch Logs API functionality to Claude, enabling natural language queries and analysis of Bedrock usage data.
How to use AWS Bedrock Logs MCP Server?
First, install the tool by following the installation instructions in the README, which includes setting up a Python virtual environment and configuring AWS credentials. Then, start the server using python cloudwatch_mcp_server.py. Finally, configure this tool with Claude Desktop by adding the server configuration to the Claude Desktop configuration file, ensuring the directory path points to the correct location of the repository on your system. You can then interact with Claude using natural language queries to analyze your Bedrock usage data.
Key features of AWS Bedrock Logs MCP Server
Model Usage Analysis
User-based Analytics
Daily Usage Reports
Token Consumption Metrics
Interactive Interface
Use cases of AWS Bedrock Logs MCP Server
Analyzing Bedrock model usage and token consumption
Tracking usage patterns and costs by user
Monitoring daily usage trends and model invocations
Identifying top users of Bedrock
Getting a daily breakdown of model invocations
FAQ from AWS Bedrock Logs MCP Server
What is MCP?
What is MCP?
MCP stands for Model Control Protocol, a framework from Anthropic.
What AWS services are required?
What AWS services are required?
AWS CloudWatch Logs and AWS credentials with CloudWatch Logs access are required.
What Python version is required?
What Python version is required?
Python 3.13 or higher is required.
How do I configure the server with Claude?
How do I configure the server with Claude?
You need to add the server configuration to the Claude Desktop configuration file, specifying the command and arguments to run the server.
What kind of queries can I run?
What kind of queries can I run?
You can ask questions like 'Show me the Bedrock usage stats for the last 7 days' or 'What's the average token consumption by model?'