mcp-server
Verified Safeby mackerelio-labs
Overview
A Model Context Protocol (MCP) server that provides an interface for AI assistants to interact with the Mackerel monitoring and APM platform, enabling retrieval and management of alerts, hosts, services, dashboards, monitors, metrics, and distributed traces.
Installation
npx -y @mackerel/mcp-serverEnvironment Variables
- MACKEREL_APIKEY
Security Notes
The server demonstrates good security practices by loading the Mackerel API key from environment variables (`MACKEREL_APIKEY`), ensuring that sensitive credentials are not hardcoded. Extensive input validation using Zod is implemented for all tool arguments, significantly reducing the risk of injection vulnerabilities. Error handling in `buildToolResponse` provides helpful, context-specific messages for 404 errors (e.g., 'Host Not Found') without exposing excessive raw API details. A simple in-memory cache is used for GET requests, which is generally safe and improves efficiency, but it assumes that the API key remains valid for cached data. No `eval` or obfuscation was found, and dependencies are from trusted sources.
Similar Servers
mcp-shark
Aggregate multiple Model Context Protocol (MCP) servers into a single unified interface with a powerful monitoring UI, enabling real-time traffic capture, logging, and AI-powered security analysis.
prometheus-mcp
Provides a Model Context Protocol (MCP) interface and CLI tools for querying Prometheus metrics, including discovery, instant/range queries, and an optional metrics exporter.
mcp-playground
A web-based developer tool for testing, inspecting, and debugging Model Context Protocol (MCP) servers, supporting OAuth integration, request logging, and interactive execution of tools, resources, and prompts.
mcp-compose
Orchestrates multiple Model Context Protocol (MCP) servers, providing a unified management interface, REST API, Web UI, and protocol translation. It enables building AI applications with secure tool access and real-time monitoring.