MCP Server for AWS Application Signals

An MCP (Model Context Protocol) server that provides tools for monitoring, analyzing, and troubleshooting AWS Application Signals services.

This server enables AI assistants to interact with AWS Application Signals to track service health, monitor SLOs (Service Level Objectives), analyze metrics, and investigate issues using distributed tracing.

Available Tools

This server provides the following tools to interact with AWS Application Signals:

• list_monitored_services - Lists all services monitored by AWS Application Signals

• get_service_detail - Gets the details healthy data for a specific service

• get_service_metrics - Queries CloudWatch metrics for the monitored services

• list_slis - Monitors SLI (Service Level Indicator) status and SLO compliance across all services

• get_slo - Retrieves detailed configuration for a specific SLO

• query_sampled_traces - Queries AWS X-Ray traces for distributed tracing analysis

• search_transaction_spans - Queries AWS X-Ray traces data

Quick Setup

Prerequisites

• AWS credentials configured (via aws configure or environment variables)

• Claude Desktop app installed

• uv package manager installed (installation guide)

  • Note: uvx is included with uv installation

Installation

You can install this MCP server in Claude Desktop using either method:

Method 1: Direct from GitHub (Recommended)

Add this configuration to your Claude Desktop settings:

Method 2: Local Installation

1. Clone this repository

2. Install dependencies (if needed):

   uv pip install -e .

3. Add to Claude Desktop configuration:

   { "mcpServers": { "appsignals": { "command": "uv", "args": [ "--directory", "/path/to/appsignals-mcp", "run", "mcp-server-appsignals" ] } } }

Amazon Q Integration

Amazon Q integration is similiar to Claude Desktop setup. First to install Amazon Q Developer and you will just add the following to your ~/.aws/amazonq/mcp.json file:

Development