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
loopwork/Companion
Companion is a native Apple-platform utility for testing and debugging Model Context Protocol servers, built on the official MCP Swift SDK. It runs on macOS, iOS and visionOS and presents a sidebar of configured servers next to a detail view. Servers are added with a plus button in the toolbar; both local servers, launched as a stdio command, and remote servers are supported, and a newly added server connects automatically. Once connected, the app lists the prompts, resources and tools the server advertises, and each section can be opened to drill into an individual item. From there the user can call a tool with arguments, generate a prompt with its arguments filled in, and download resources; selecting the parent entry in the sidebar shows information about the server itself. This makes it a graphical alternative to reading raw protocol traffic when checking whether a server exposes what its author intended and whether its tools behave correctly. The app is distributed as a signed download from the GitHub releases page and through a Homebrew cask, and requires macOS 15 or later; building from source needs Xcode 16.3 or newer, with deployment targets of macOS 15, iOS and iPadOS 16 and visionOS 2. The README states plainly that the project is in early development and still lacks several important pieces of the protocol, specifically authentication, roots and sampling, and it points readers who need fuller coverage to the official MCP Inspector. The project is MIT licensed and is not affiliated with Apple; its icon is described as a nod to the Finder icon and to henohenomoheji, the face Japanese schoolchildren draw from hiragana characters.
https://github.com/loopwork/Companion
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.
MCPJam/inspector
MCPJam Inspector is a developer tool for testing and debugging MCP servers, supporting multiple protocols and LLM interaction, designed to streamline MCP 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.