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/bahayonghang/drawio-skillsWrote 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/bahayonghang/drawio-skills/drawio-drawio)<a href="https://agentmods.dev/mcp/bahayonghang/drawio-skills/drawio-drawio"><img src="https://agentmods.dev/badge/mcp/bahayonghang/drawio-skills/drawio-drawio/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/bahayonghang/drawio-skills/drawio-drawio"><img src="https://agentmods.dev/badge/mcp/bahayonghang/drawio-skills/drawio-drawio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
drawio 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- drawio — 100% identical, 0 lines differ
What it actually says
{
"drawio": {
"command": "npx",
"args": [
"--yes",
"@next-ai-drawio/[email protected]"
]
}
}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.
- 10d ago First seen · 9 lines scan A 6893510d5034
drawio is an MCP server published in the GitHub repository bahayonghang/drawio-skills (281 stars, last pushed 2d 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 2026-08-30.
Other mcp servers, from other repositories
ui-craft
ui-craft MCP server — deterministic design-quality gate (anti-slop, tokens, acceptance-bar, score). Runs locally from the ui-craft-mcp npm package.
lucide-icons
This project, lucide-react-mcp, is a Model Context Protocol (MCP) server built with Bun and the MCP TypeScript SDK. It exposes Lucide React icons as resources and tools, enabling LLMs and agentic applications to search for and utilize icons. Key features. Runs locally from the lucide-icons-mcp npm package.
drawio
MCP server "drawio" as configured in os-tack/fcp-drawio. Runs locally from the @os-tack/fcp-drawio npm package.
miro
MCP server "miro", hosted remotely at mcp.miro.com, as configured in daddia/claude-for-strategy.
diagram-master
MCP Server for generating Draw.io compatible diagrams from natural language prompts. Runs locally from the diagram-master npm package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.