inspector
Verified Safeby mcp-use
Overview
Interactive developer tool for testing and debugging MCP (Model Context Protocol) servers, with support for MCP-UI and OpenAI Apps SDK widgets.
Installation
npx @mcp-use/inspectorEnvironment Variables
- MCP_USE_ANONYMIZED_TELEMETRY
- POSTHOG_API_KEY
- POSTHOG_HOST
- SCARF_API_KEY
- PORT
- NODE_ENV
Security Notes
The project demonstrates good security practices for a developer tool. It handles LLM API keys and OAuth tokens, which are sensitive, primarily client-side via browser local storage, and can be proxied through the Inspector server. Telemetry collection is anonymized and opt-out via `MCP_USE_ANONYMIZED_TELEMETRY` environment variable or local storage settings. External requests are made for favicons and LLM APIs. The primary inherent risks stem from its core functionality: connecting to arbitrary, potentially untrusted MCP servers defined by the user, and facilitating interactions with external LLM services.
Similar Servers
inspector
MCPJam Inspector is a desktop and web application designed for testing, debugging, and managing Model Context Protocol (MCP) servers, serving as a 'Postman for MCP'. It allows users to connect to MCP servers, explore their tools, resources, and prompts, perform API calls, manage OAuth authentication flows, run AI model evaluations, and monitor server-side RPC traffic.
mcp-interviewer
A Python CLI tool designed to evaluate, test, and generate reports on Model Context Protocol (MCP) servers to ensure compatibility and quality for LLM agent use cases.
mcp-servers
Provides a curated collection of Model Context Protocol (MCP) server configurations to enable AI agents to interact with various developer tools and services.
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.