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/RedHold/diagrams-mcp-app-coreWrote 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/redhold/diagrams-mcp-app-core/diagrams-so-mcp)<a href="https://agentmods.dev/mcp/redhold/diagrams-mcp-app-core/diagrams-so-mcp"><img src="https://agentmods.dev/badge/mcp/redhold/diagrams-mcp-app-core/diagrams-so-mcp/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/redhold/diagrams-mcp-app-core/diagrams-so-mcp"><img src="https://agentmods.dev/badge/mcp/redhold/diagrams-mcp-app-core/diagrams-so-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
diagrams-so-mcp 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
{
"diagrams-so-mcp": {
"command": "npx",
"args": [
"-y",
"@diagrams-so/mcp"
],
"env": {
"DIAGRAMS_API_KEY": "",
"DIAGRAMS_API_BASE": "https://api.diagrams.so/api/v2",
"DIAGRAMS_API_TIMEOUT_MS": "450000"
}
}
}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 · 14 lines scan A b404aab2e354
diagrams-so-mcp is an MCP server published in the GitHub repository RedHold/diagrams-mcp-app-core (0 stars, last pushed 4d ago), licensed Apache-2.0. 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
flowgraf-mcp
Flowgraf MCP server — create and edit clean, editable architecture diagrams from your AI agent (Claude Code, Cursor, Windsurf). Returns an SVG plus a link to a live, editable canvas. Runs locally from the flowgraf-mcp npm package.
drawx-mcp-server
Generate draw.io diagrams and architecture designs from natural language, via the DrawX API. Runs locally from the @drawx/mcp-server npm package. Needs 2 environment variables to run.
s3
AWS S3 MCP — list buckets, browse objects, upload/download, presigned URLs. Runs locally from the mcp-server-s3 npm package.
archdiagram
MCP server "archdiagram" as configured in bharathgnana/archdiagram. Runs locally from the archdiagram Python package.
codepic
AI agent draws editable hand-drawn diagrams (flowchart, ER, architecture) via MCP, not static images. Remote server at codepic.cc.
plumb-mcp
Figma → code MCP: no rate limits, no metered quotas, verification loop. Works on every Figma plan. Runs locally from the plumb-mcp npm package. Needs 2 environment variables to run.