Debugging MCP servers

A server here finding and fixing bugs in running software: debuggers, errors, stack traces.

Not here: uptime monitoring.

407servers
92 remote315 localTagged by Odel's AI, which can make mistakes

Best fit

203 made for this, ranked by starsRemoteLocal
  1. Probe Kit @mybolide/mcp-probe-kitSpec-driven dev workflow MCP: start_* orchestration, memory, GitNexus, quality gates.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.39 GitHub stars.
  2. MsgPack (LsMsgPack) @mlsomers/lsmsgpackDecodes MsgPack (LsMsgPack schemas, type ids) as text and reads it from variables while debugging.Not assessed yet.Runs on your machine, installed from NuGet.36 GitHub stars.
  3. Brave DevTools MCP @triuzzi/brave-mcpMCP server and CLI for Brave DevTools5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.36 GitHub stars.
  4. Beckett - MCP for Godot @beckettlab/beckett-godot-mcpMCP server embedded in the Godot 4 editor; drive Godot with AI, zero sidecar.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.36 GitHub stars.
  5. J-Link MCP @klievan/jlink-mcpDebug embedded firmware on real hardware: J-Link probes, Cortex-M faults, RTT logs, GDB.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.35 GitHub stars.
  6. Scout Local @scoutapm/scout-mcp-localAn MCP server for Scout Monitoring data interactions.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.30 GitHub stars.
  7. Hera Agent Unity @notnull92/hera-agent-unityControl and verify a live Unity Editor through a local, low-token MCP server.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.29 GitHub stars.
  8. Sfcc Dev @taurgis/sfcc-dev-mcpMCP server for Salesforce B2C Commerce Cloud development assistance5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.28 GitHub stars.
  9. Xdebug @kpanuragh/xdebugMCP server for PHP Xdebug debugging with breakpoints, stepping, and variable inspection4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.28 GitHub stars.
  10. NEAT @neat-technologies/neatFused graph of your codebase — static code + runtime OTel — for AI agents, over MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.22 GitHub stars.
  11. DevTool MCP @standardbeagle/devtool-mcpDevelopment tooling MCP server with process management, proxy, and frontend diagnostics4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
  12. Zuul @imatza-rh/mcp-zuulZuul CI — build failure analysis, log search, pipeline status, and job configuration4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.21 GitHub stars.
  13. CacheOverflow @getcacheoverflow/cacheoverflowMCP server for cache.overflow - AI agents sharing knowledge with AI agents8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
  14. glass @fixed-width/glassMCP server giving a coding agent a build→see→interact→debug loop over native GUI apps.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.18 GitHub stars.
  15. Agentic HIL @agentic-hil/agentic-hilDevelop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.17 GitHub stars.
  16. WPF Visual Tree @faze79/wpf-visual-treeLet AI agents inspect and drive running WPF apps: tree, bindings, screenshots, clicks, text input.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.17 GitHub stars.
  17. Weapp Agent @chaixueyuan/weapp-agent-mcpAgent-first MCP server for WeChat Mini Program debugging & automation via WeChat DevTools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.17 GitHub stars.
  18. ASP.NET Core Debugger — MCP Server for AI Agents @magna-nz/aspnetcore-debugger-mcpMCP server giving AI agents interactive .NET / ASP.NET Core debugging via netcoredbg + DAP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.15 GitHub stars.
  19. N8n @ratamaha-git/n8n-mcpMCP server for n8n: generate, lint, explain failed executions, drive live n8n via REST.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
  20. WinDbg @glslang/windbg-mcpWinDbg/DbgEng over MCP: crash dumps, live user & kernel, driver IOCTLs, and TTD.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.14 GitHub stars.
  21. Android @us-all/androidAndroid MCP — ADB-based device, apps, UI, logcat, emulator, files, system, debug7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
  22. Memorydetective @carloshpdoc/memorydetectiveiOS leak/perf debugging via MCP: memgraph cycles, .trace analysis, SourceKit-LSP bridging.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
  23. GodotLens @pzalutski-pixel/godotlensGodot's own view of your GDScript project: navigation, diagnostics, engine API, scene checks4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
  24. Dbgprobe @es617/dbgprobe-mcp-serverLet AI agents interact with debug probes — connect, flash, read/write memory, and reset.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.10 GitHub stars.