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
apify/tester-mcp-client
Tester MCP Client is an open-source Model Context Protocol client packaged as an Apify Actor. It connects to a remote MCP server over the streamable HTTP transport and exposes a browser-based chat interface so a developer can exercise that server interactively. After the Actor starts, its log prints a per-run URL, and opening it serves a small static front end from the public directory. The browser keeps a Server-Sent Events stream open against GET /sse and posts user queries to POST /message, while the Actor itself speaks streamable HTTP to the MCP server under test. Keeping the bridging logic on the client side means the tested MCP server stays unmodified. For each query the Actor calls a large language model, orchestrates any tool calls the model requests, and emits the resulting assistant text and tool-usage blocks back over SSE, so the chat view shows both the conversation and the individual tool invocations with their results. Configuration through the Apify UI or API covers the MCP server URL, the system prompt and an API key, and Authorization headers are supported for servers that require authentication. Tool lists can be selected dynamically when the target server supports it, which the project demonstrates against the Apify MCP Server and its thousands of Actor-backed tools. Claude Sonnet and Claude Haiku models are supported, with deprecated model ids migrated automatically to current equivalents, and users may supply their own LLM provider key instead of paying per answered query. Billing follows the Apify pay-per-event model, charging for Actor start, running time and answered queries. The project targets people who build MCP servers and want a hosted, throwaway client to verify transport behaviour, authentication and tool execution end to end.
https://github.com/apify/tester-mcp-client
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.