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
workbackai/mcp-nodejs-debugger
The MCP Node.js Debugger is a specialized MCP (Model Context Protocol) server designed to integrate with AI coding assistants such as Cursor and Claude Code, enabling them to debug Node.js applications dynamically at runtime. This tool allows these AI assistants to set breakpoints, inspect runtime states, and interact with the Node.js debugging protocol to provide real-time debugging assistance. The debugger works by connecting to a Node.js server running in debug mode (using the --inspect flag), allowing the AI to access the runtime environment and help developers identify and resolve issues more efficiently. The project provides detailed instructions for integrating the MCP Node.js Debugger with both Cursor and Claude Code AI assistants. For Cursor, users add the debugger to the MCP servers configuration file and run their Node.js application in debug mode. They can then ask Cursor to debug the application, set breakpoints, and inspect runtime state visually. For Claude Code, the debugger is added via a command-line interface, and users can interact with Claude Code to debug runtime errors by setting breakpoints and inspecting variables. The debugger supports practical use cases such as setting breakpoints in specific files and lines, listing all breakpoints, and executing JavaScript code snippets within the Node.js runtime to inspect variables and application state. The README includes examples demonstrating how to debug a simple Node.js app and handle common runtime errors, such as database connection issues with Mongoose. Overall, the MCP Node.js Debugger enhances the capabilities of AI coding assistants by providing them with direct access to the Node.js runtime environment, enabling more effective and interactive debugging sessions. This project is highly relevant to the Model Context Protocol ecosystem as it extends MCP functionality to runtime debugging of Node.js applications, facilitating AI-assisted development workflows.
https://github.com/workbackai/mcp-nodejs-debugger
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.
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.