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
rust-mcp-stack/mcp-discovery
MCP Discovery is a utility for inspecting MCP servers rather than a server itself. Given a server's launch command or endpoint, it acts as a client, performs the handshake, and reports what the server actually publishes — its declared capabilities, the tools with their input schemas, and the resources and prompts it offers. Output can be printed to the terminal or written to files as Markdown, HTML, plain text or JSON, and a custom template can be supplied for any other format. A particularly practical feature is updating an existing file in place, which lets a project keep a generated capabilities table inside its own README and refresh it as the server changes, rather than maintaining documentation by hand that silently drifts from the implementation. Two other uses follow naturally: verifying that a server under development exposes what its author intended, and comparing servers before choosing one to install. It is written in Rust and distributed as a standalone binary, so it adds no runtime dependency to the machine it inspects from, and the project publishes its own documentation site with command examples. The audience is MCP server authors documenting their work, and anyone auditing what a third-party server would expose before adding it to a client.
https://github.com/rust-mcp-stack/mcp-discovery
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.