- OpenOCD Debugger @microhenrio/openocd-mcpDebug microcontrollers via OpenOCD: flash, breakpoints, memory, registers and variables.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Feedthrough @feedthrough/feedthroughDebug bridge inside your web app: an agent reads the DOM, console and network. Any browser.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Debugium @algiras/debugiumAI-driven live debugger with MCP bridge for Python, JS, TS, Rust, Java, C/C++4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- joLink @l1ch404/jolink-runtimeA lightweight Java IDE for AI agents: incremental builds, fast tests, HotSwap and live debugging.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Claimidx @claimidx/claimidxPrior art for AI agents. init wires DID/MCP; claim --yes puts DID on commons (ask alone does not).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Qwen DAP MCP @slp-dev1/qwen-dap-mcpNative runtime debugging via DAP-to-MCP for crashes, hangs, dumps, symbols, and forensics.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- specmate @alele496/bsv-specmateBSV coding knowledge engine for AI agents — pre-compile traps and post-compile diagnosis.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- CyberHuaTuo @jinning6/cyberhuatuoGold-first AI-agent traceback diagnosis, exact fixes, verification, and reusable prescriptions.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Forkmind @medhovarsh/forkmindBranchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Mushi Mushi @kensaurus/mushi-mushiThe bug mediator for AI-built apps: plain-English diagnosis + a ready fix, in your editor.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- Fixgraph @jawdat6/fixgraph-mcpSearch 25K+ verified engineering fixes by error or technology. For developers and AI agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Local LLM Worker @joblessjoe/local-llm-workerLocal LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Smolmux GDB @magnusmalm/smolmux-gdb-mcpGDB/SWD MCP server over a smolmux broker: breakpoints, memory, Cortex-M fault decode, board probing.Not assessed yet.Runs on your machine, installed from a package registry.2 GitHub stars.
- x64dbg MCP @rison1337/x64dbg-mcpWindows x64dbg/x32dbg debugging with guarded sessions, breakpoints, memory and runtime evidence.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- FlutterSDK Telescope @fluttersdk/telescopeInspect a running Flutter app: HTTP traffic, logs, exceptions and queries. Debug only.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
- Gdharness @aureliolo/gdharnessA harness for driving a Godot 4 project from an agent: addons, runtime bridge, MCP server, CLI.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- DevCDP @dayananda-d/devcdpChrome DevTools for AI assistants: console, network, DOM, source maps, breakpoints, live variables.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- UI Debugger @developerz-ai/ui-debugger-mcpAutonomous UI debugging MCP server: an agent drives the browser/desktop, reports bugs + UX issues.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Incident Response MCP for Apache Airflow @madamak/apache-airflow-mcp-serverDiagnose Airflow failures from UI links with bounded logs and optional recovery actions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Hotato @attenlabs/hotatoOpen-source, self-hosted conversation QA for voice agents. MIT.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Devloop @vincentvella/devloopBrowser + dev-server logs on one correlated timeline, for Claude Code and AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- MCP Debug Recorder @oaslananka/debug-recorder-mcpRecord debug sessions, commands, failed attempts, and successful fixes in local SQLite storage.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Statecli @charo360/statecliState replay and self-debugging for AI agents. Track, replay, undo, checkpoint.14% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Source Map Parser @masonchow/source-map-parser-mcpParse JavaScript error stack traces back to original source code using source maps5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
