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/hustcc/mcp-mermaidWrote 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/hustcc/mcp-mermaid/hustcc-mcp-mermaid)<a href="https://agentmods.dev/mcp/hustcc/mcp-mermaid/hustcc-mcp-mermaid"><img src="https://agentmods.dev/badge/mcp/hustcc/mcp-mermaid/hustcc-mcp-mermaid/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/hustcc/mcp-mermaid/hustcc-mcp-mermaid"><img src="https://agentmods.dev/badge/mcp/hustcc/mcp-mermaid/hustcc-mcp-mermaid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
hustcc-mcp-mermaid 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 13d 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
{ "hustcc-mcp-mermaid": { "url": "https://server.smithery.ai/@hustcc/mcp-mermaid/mcp", "type": "streamable-http" } }
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.
- 13d ago First seen · 6 lines scan A f5b047f64614
hustcc-mcp-mermaid is an MCP server published in the GitHub repository hustcc/mcp-mermaid (634 stars, last pushed 4mo 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
software-design-mermaid-mcp
MCP server "software-design-mermaid-mcp" as configured in wzh4464/software-design-mermaid-mcp. Runs locally from the software-design-mermaid-mcp npm package.
mcp-diagram-server
MCP server "mcp-diagram-server" as configured in angrysky56/mcp-diagram-server. Runs locally from the mcp-diagram-server Python package.
mermaid-svg
MCP server "mermaid-svg" as configured in jagadeesh52423/mermaid-svg-mcp. Runs /Users/jagadeeshpulamarasetti/OwnCode/mermaid-svg-mcp/dist/index.js with node.
inkscape-mcp
MCP server "inkscape-mcp" as configured in sandraschi/inkscape-mcp. Launched with uv --directory D:/Dev/repos/inkscape-mcp run inkscape-mcp.
mobbin
Search real-world UI & UX design references for mobile apps, web apps, and websites with Mobbin. Remote server at api.mobbin.com.
mcp-design-system-extractor
MCP server for Storybook design systems — extract component HTML, styles and metadata. Runs locally from the mcp-design-system-extractor npm package. Needs 3 environment variables to run.