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.
git 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/plugins/svnscha/mcp-windbg/mcp-windbg-skills)<a href="https://agentmods.dev/plugins/svnscha/mcp-windbg/mcp-windbg-skills"><img src="https://agentmods.dev/badge/plugins/svnscha/mcp-windbg/mcp-windbg-skills/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/plugins/svnscha/mcp-windbg/mcp-windbg-skills"><img src="https://agentmods.dev/badge/plugins/svnscha/mcp-windbg/mcp-windbg-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-windbg-skills 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.
What it actually says
{
"name": "mcp-windbg-skills",
"source": "./plugins/mcp-windbg-skills",
"strict": false,
"description": "WinDbg skills for crash dump analysis, remote debugging, kernel debugging, and setup diagnostics.",
"version": "1.3.0",
"skills": [
"./skills/analyze-dump",
"./skills/debug-remote",
"./skills/kernel-debug",
"./skills/windbg-doctor"
],
"author": {
"name": "Sven Scharmentke"
},
"homepage": "https://svnscha.github.io/mcp-windbg/reference/plugin/",
"repository": "https://github.com/svnscha/mcp-windbg",
"license": "MIT",
"category": "development"
}What it installs
The manifest is a name and a version. 4 skills travel with it, and installing the plugin installs all of them — 195 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside marketplace.json#mcp-windbg-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 20 lines scan A b9f4a935af95
mcp-windbg-skills is a plugin published in the GitHub repository svnscha/mcp-windbg (1,567 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-10.
Other plugins, from other repositories
chrome-devtools-mcp
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer.
chrome-devtools-mcp
MCP configuration declaring 1 server: chrome-devtools.
monday.com
Connect your AI agents to monday.com — your work OS for managing projects, tasks, and everyday work.
oneskills
OneScience / OneSkills skills for AI-native scientific research workflows, coding, runtime submission, debugging, and environment setup.
mcp-migration
Diagnose and carry out the migration of an MCP server to the 2026-07-28 specification. Runs a deterministic rule engine over the code, then walks the remediation per finding: stateless transport, OAuth 2.1, the deprecated capabilities, and the SDK v2 rename.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.