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/TheoEwzZer/WinSight-MCPWrote 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/mcp/theoewzzer/winsight-mcp/winsight)<a href="https://agentmods.dev/mcp/theoewzzer/winsight-mcp/winsight"><img src="https://agentmods.dev/badge/mcp/theoewzzer/winsight-mcp/winsight/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/mcp/theoewzzer/winsight-mcp/winsight"><img src="https://agentmods.dev/badge/mcp/theoewzzer/winsight-mcp/winsight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
winsight 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 12d 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.
What it actually says
{
"winsight": {
"command": "uv",
"args": [
"--directory",
"D:/repositories/WinSight-MCP",
"run",
"python",
"-m",
"winsight_mcp"
]
}
}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.
- 12d ago First seen · 13 lines scan A fd7071d67d05
winsight is an MCP server published in the GitHub repository TheoEwzZer/WinSight-MCP (3 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.
Other mcp servers, from other repositories
plonk
MCP server for Plonk, a macOS window manager: zones you draw yourself, workspaces, keep-awake, screenshots and on-device OCR, as tools an agent can call. Runs locally from the plonk-mcp npm package.
plonk
MCP server for Plonk: macOS window zones, workspaces, keep-awake, screenshots and on-device OCR. Runs locally from the plonk-mcp npm package.
site-shot-mcp
Website screenshots for AI agents: full-page, country proxies, ad & cookie-banner removal. Runs locally from the site-shot-mcp npm package. Needs 1 environment variable to run.
screenshot-pdf
Capture screenshots (PNG/JPEG/WebP) and generate PDFs from any URL. x402 payments. Remote server at screenshot-pdf.api.klymax402.com.
codex-win-to-wsl
MCP server "codex-win-to-wsl" as configured in Yuyu123fish/codex-win-to-wsl. Runs ./mcp/server.mjs with node.
capture-screen
MCP server "capture-screen" as configured in ochtum/CaptureScreenMCP. Launched with CaptureScreenMcp. Needs 3 environment variables to run.