Arize-ai/phoenix
Phoenix is an open-source AI observability platform for experimentation, evaluation, and troubleshooting of large language model applications, supporting multiple frameworks and LLM providers with flexible deployment options.
Awesome MCP › Testing & Debugging
MCPJam/inspector
MCPJam Inspector is a comprehensive developer tool designed specifically for testing and debugging MCP (Model Context Protocol) servers. It supports multiple communication protocols including STDIO, SSE, and Streamable HTTP, allowing developers to connect to any MCP server seamlessly. The tool enhances the development workflow by providing features such as tool execution with live parameter input, which facilitates easy debugging of server errors. A notable new feature is the integration of LLM (Large Language Model) tool interaction, enabling developers to test their MCP servers against real LLMs, thus bridging the gap between server functionality and AI capabilities. The inspector offers an enhanced logging experience to aid in debugging and includes quality of life improvements like saving requests, supporting multi-server connections, and saving connection configurations. It is built as a modern monorepo with three main components: a React and TypeScript frontend, an Express.js backend with WebSocket support, and a command-line interface (CLI) for ease of use. The project supports running via Node.js or Docker, making it flexible for different development environments. MCPJam Inspector is a fork of the original @modelcontextprotocol/inspector with additional enhancements and improvements. It is actively maintained with a roadmap that includes UI/UX improvements, AI-powered parameter completion, multi-provider LLM support, security scanning, and plans for an Electron desktop application. The project encourages community contributions and follows modern development practices with tools like Prettier and ESLint for code quality. Overall, MCPJam Inspector is a powerful and user-friendly tool tailored for developers working within the MCP ecosystem, streamlining the process of server testing, debugging, and interaction with AI models.
https://github.com/MCPJam/inspector
Also in Testing & Debugging
modelcontextprotocol/inspector
MCP Inspector is a developer tool that provides a visual UI and CLI for testing, debugging, and interacting with Model Context Protocol (MCP) servers, enhancing MCP server development workflows.
Arize-ai/openinference
OpenInference is an open-source extension of OpenTelemetry that provides comprehensive tracing and observability for AI applications, including support for the Model Context Protocol (MCP).
LSTM-Kirigaya/openmcp-client
OpenMCP is an all-in-one VSCode plugin that integrates development, testing, and management tools for Model Context Protocol (MCP) server debugging and large model interaction.
workbackai/mcp-nodejs-debugger
MCP Node.js Debugger is an MCP server that enables AI coding assistants like Cursor and Claude Code to debug Node.js applications at runtime by setting breakpoints and inspecting runtime state.
modelscope/MCPBench
MCPBench is an open-source evaluation framework for benchmarking Model Context Protocol (MCP) servers across Web Search, Database Query, and GAIA tasks, measuring accuracy, latency, and token consumption under consistent LLM and agent settings.
hyprmcp/jetski
Open source MCP analytics and authentication platform that deploys an OAuth gateway in front of MCP servers and aggregates prompt analytics, generated setup instructions and real time debug logs.
loopwork/Companion
Swift app for macOS, iOS and visionOS that connects to local and remote MCP servers to browse and exercise their prompts, resources and tools while testing and debugging.