Debugging

MCP server for launching and debugging Electron apps via Chrome DevTools Protocol

LLui MCP server — LLM debug tools via Model Context Protocol

Debug both ends of MCP Apps — render your server's app in a Playwright browser with 7 automated diagnostics, 12 under --profile (npx mcp-app-debug <server-url>), or grade a HOST's MCP Apps conformance with a probe fixture server (npx mcp-app-debug host).

MCP server for GlitchTip error monitoring integration

Model Context Protocol (MCP) server for Bugsink error tracking — browse teams, projects, issues, events, stacktraces and releases from any MCP-compatible client

Select a layout layer on a live web or Android UI, move it, and hand the edit to any MCP agent.

Catch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI.

MCP server for React Native — drive, inspect, and debug running RN apps from AI agents via the real OS gesture pipeline

Enhanced MCP server for code reasoning using sequential thinking methodology, optimized for programming tasks

Lujo-MCP — MCP Runtime Debugging Context Server for AI coding agents. Gives Claude, Cursor, Trae and any MCP-compatible client real runtime debugging context: browser errors, console logs, network failures, UI interaction traces and session context. Zero-

MCP server for React Native runtime debugging — zero-config access to Redux state, AsyncStorage, actions, logs, network, and profiling from your running app

Record debug sessions, commands, failed attempts, and successful fixes in local SQLite storage.

LangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like)

Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.

Agent Debug MCP: local MCP server (stdio + streamable HTTP) bridging the Agent Debug MCP Chrome extension to coding agents, with built-in browser automation (embedded Playwright MCP re-exported as page_* tools), a CDP endpoint for external Playwright clie

Piperace — the missing toolkit for localhost: public tunnels, trusted local HTTPS domains and traffic inspection, with an MCP server for AI agents. One binary, one command.

Records MCP tool calls and itemises the token cost each server adds to your context.

X-ray vision for AI agent sessions — a transparent HTTP proxy and dashboard for Claude Code

MCP server that gives AI clients runtime feedback from Godot (errors / scene tree / node props / screenshot) for an AI self-correction loop.

GoPeak — MCP server for trusted Godot 4 workflows with compact/dynamic tool profiles, setup-gated LSP/DAP/runtime integrations, and migration-safe legacy compatibility.