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
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.
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 is a developer tool for testing and debugging MCP servers, supporting multiple protocols and LLM interaction, designed to streamline MCP development workflows.
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).
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.
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.
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.
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.
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.
A security scanner for MCP server implementations that detects hardcoded credentials, tool poisoning, prompt injection, protocol violations and other vulnerability classes.
Node.js package and GitHub Action that grades the tools of an MCP server with LLM-scored evaluations declared in TypeScript or YAML, posts results on pull requests, and adds metrics and tracing to a server.
An MCP server that writes, launches and manages other MCP servers as child processes, so new tools can be created and updated at runtime.
A Rust command-line tool that connects to an MCP server, enumerates its tools, resources and capabilities, and documents them as Markdown, HTML, text, JSON or a custom template.
A standalone Apify Actor that acts as an MCP client over streamable HTTP and renders the conversation, tool calls and results in a chat-like web UI for testing remote MCP servers.