mcp-windbg is a Model Context Protocol server that lets AI models control WinDbg, the Windows debugger used to inspect crash dumps and debug user-mode or kernel software. Developers and investigators use it to run debugger commands, examine failures, and manage multiple live debugging sessions through natural-language requests. The catalogue add-ons connect coding agents to this debugging workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add svnscha/mcp-windbg --skill windbg-doctorgit clone --depth 1 https://github.com/svnscha/mcp-windbgWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/svnscha/mcp-windbg/windbg-doctor)<a href="https://agentmods.dev/skills/svnscha/mcp-windbg/windbg-doctor"><img src="https://agentmods.dev/badge/skills/svnscha/mcp-windbg/windbg-doctor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/svnscha/mcp-windbg/windbg-doctor"><img src="https://agentmods.dev/badge/skills/svnscha/mcp-windbg/windbg-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 35 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.00787 |
| Opus 5 | $0.00028 | $0.00394 |
| Sonnet 5 | $0.00011 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
windbg-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check the debugging setup
MCP connection
Use the existing mcp-windbg MCP connection, whether it is launched by a plugin, a native executable, Python, or an HTTP service. Tool names below are base names; resolve them against the tools exposed by that connection rather than assuming a plugin-specific prefix. Keep each session on the server that opened it. If multiple servers match, use the user's selected server or ask which one. If the required tools are unavailable, report the missing connection or tool and help check its configuration; do not register a second server.
Diagnose why mcp-windbg is not working, or confirm it will before someone relies on it. Report findings together at the end, not one command at a time.
Checks
Inspect the configured MCP transport and launch command first. Run host checks on the machine running the server, using its available shell. For an HTTP service, local client checks do not describe the server; use server diagnostics or ask its operator for evidence and mark unavailable checks as unverified.
1. Tools reachable. Call list_dumps through the configured connection.
A successful response, including an empty list, proves the MCP round trip works;
it does not prove that CDB or KD can start. If connection fails, inspect the
client's MCP status and server logs.
2. Platform and debugger. The server host must be Windows. Check configured
--cdb-path / --kd-path overrides and the debugger locations the server searches:
C:\Program Files (x86)\Windows Kits\10\Debuggers\x64\cdb.exe
%LOCALAPPDATA%\Microsoft\WindowsApps\cdbX64.exe
Check KD as well for kernel debugging. If the debugger is missing, point at aka.ms/windbg or the Windows SDK's Debugging Tools for Windows. Do not infer that the debugger is missing from a client-side path check.
3. Launcher. Check only the runtime used by the configured server command:
uvx: checkuv --versionand run the configured package spec with--help, preserving its version pin. Resolution failures can indicate network or proxy problems. uv is required only for this launch method.- Python or a console entry point: use the configured interpreter or executable
with
--help(for examplepython -m mcp_windbg --help). - Native executable: check that exact executable with
--help; do not require Python or uv. - HTTP: check the configured endpoint and server logs; do not launch a local replacement server.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +15 lines 3c647726fbeb
- 11d ago First seen · 54 lines · 56 tokens per session scan A 829e6caf33b4
windbg-doctor is a skill published in the GitHub repository svnscha/mcp-windbg (1,567 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 787 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
post-mortem
Diagnose instruction defects and optionally submit Rosetta GitHub issue.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
solr-query
To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.
debugging
To investigate errors, test failures, and unexpected behavior — root cause before fix.
self-learning
MUST activate on: execution failure/error, mistake, wrong/unexpected result, expected≠actual mismatch, 2 consecutive mismatches, unhappy/upset user, user asks why something failed/didn't work.