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
OpenMCP is a comprehensive VSCode plugin designed specifically for the development, testing, and management of Model Context Protocol (MCP) servers. It integrates multiple tools into a single platform to facilitate efficient debugging and interaction with large models. The plugin combines an integrated inspector and basic MCP client functions, allowing developers to seamlessly develop and test MCP servers within the same environment. OpenMCP supports testing of resource protocols, tools, and prompts for MCP servers, and includes an "Interactive Testing" module for large model interaction testing. It also features a project-level management panel that simplifies MCP project management at both the project and global levels, supporting multiple large models simultaneously. The project adopts a layered modular design, enabling it to be implemented in various modes across different platforms, including web, VSCode plugin, desktop app, and even a QQ bot. The core components include a renderer for frontend UI and an OpenMCPService for backend logic. The modular architecture allows for flexibility and extensibility, with components such as Nginx for web reverse proxy, Electron for desktop packaging, and Lagrange.OneBot for protocol adaptation in the QQ bot. OpenMCP's feature roadmap includes support for cost analysis in chat mode, custom large model integration compatible with OpenAI, debugging multiple MCP servers simultaneously, online verification via large models, saving debugging work, system prompt management, and built-in OCR for character recognition. The project also plans to implement security features like MCP security checks to prevent prompt injection and a tool-wise logging system. Development involves separate modules for renderer (frontend UI), service (backend test components), and VSCode plugin definitions. The project provides commands for setup, development server start, and building for deployment, including building the VSCode extension. Continuous integration pipelines ensure build and unit test reliability. Overall, OpenMCP is a powerful and versatile tool tailored for MCP server developers, streamlining the entire development lifecycle from coding to testing and management within a unified interface.
https://github.com/LSTM-Kirigaya/openmcp-client
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).
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.