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 analyze-dumpgit 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/analyze-dump)<a href="https://agentmods.dev/skills/svnscha/mcp-windbg/analyze-dump"><img src="https://agentmods.dev/badge/skills/svnscha/mcp-windbg/analyze-dump/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/analyze-dump"><img src="https://agentmods.dev/badge/skills/svnscha/mcp-windbg/analyze-dump.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00782 |
| Opus 5.5 | $0.00022 | $0.00313 |
| Sonnet 5.5 | $0.00011 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
analyze-dump 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 25d ago.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze a Windows crash dump
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.
Work through a .dmp file with the mcp-windbg tools and report what actually
crashed, not just what the debugger printed.
Getting a dump path
If the user gave a path, use it. If not, call list_dumps to show what is in
the local crash dump directory and ask which one. Do not guess.
Kernel dumps
A blue screen leaves a kernel dump: MEMORY.DMP, or a file under
C:\Windows\Minidump. Open it with open_kd_dump instead of open_cdb_dump,
and use run_kd_command and close_kd_session in place of the cdb tools below.
The triage is the same, led by !analyze -v and the bugcheck code; kernel
follow-ups include !thread, !process 0 0, lmvm <driver>, and !irql.
Triage
open_cdb_dumpwith the path. Passinclude_stack_trace: true; addinclude_modulesorinclude_threadsonly if the question calls for them. Keep the returnedsession_idfor every follow-up call.run_cdb_commandwith!analyze -v. This is the single most informative command and belongs in every triage.- Follow the evidence with further
run_cdb_commandcalls. Useful next steps:k/kbfor the call stack with argumentslmto see whether the faulting module has symbols.exr -1,.ecxrfor the exception record and contextdt,dx,db/ddto inspect the data the crash implicates
close_cdb_sessionwhen you are done.
Reporting
Lead with the answer: what failed, where, and why, in the first two sentences. Then support it - exception code and its meaning, the faulting frame, and the specific evidence that points there.
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.
- 25d ago Changed · +8 lines · +9 tokens per session 027a3388154a
- 1mo ago Changed · +10 lines c85f0e45491f
- 1mo ago First seen · 48 lines · 47 tokens per session scan A 8d4d5814a3cd
analyze-dump is a skill published in the GitHub repository svnscha/mcp-windbg (1,633 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 782 once invoked, about $0.0002 per session on Opus 5.5. 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.