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
kapilduraphe/mcp-watch
MCP Watch is a TypeScript command-line scanner that audits Model Context Protocol server code for security problems. It runs against a GitHub repository URL or a local project directory and reports findings across a dozen vulnerability families specific to MCP: hardcoded API keys and insecurely stored credentials; tool poisoning, where malicious instructions are hidden inside a tool description; parameter injection through undocumented magic parameters that extract model context; prompt injection and prompt manipulation; tool mutation, where a server changes its advertised tools after approval, enabling rug-pull attacks; conversation exfiltration triggers that copy chat history out; ANSI escape-sequence injection used to hide text from human reviewers; MCP protocol violations; ordinary input-validation flaws such as command injection, SSRF and path traversal; server spoofing, where a server impersonates a well-known service; toxic data-flow patterns; and excessive permissions or weak access control. Installation is a global npm package, after which scan and scan-local subcommands produce the report. The scanner is static — it reads source rather than executing the server — so it fits into review and continuous-integration workflows before a server is published or installed. It is aimed at people writing MCP servers who want a checklist applied mechanically, and at reviewers evaluating third-party servers before allowing them into a client configuration.
https://github.com/kapilduraphe/mcp-watch
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.