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/tathagat22/plumb-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/tathagat22/plumb-mcp/plumb-mcp)<a href="https://agentmods.dev/mcp/tathagat22/plumb-mcp/plumb-mcp"><img src="https://agentmods.dev/badge/mcp/tathagat22/plumb-mcp/plumb-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/tathagat22/plumb-mcp/plumb-mcp"><img src="https://agentmods.dev/badge/mcp/tathagat22/plumb-mcp/plumb-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
plumb-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 11d 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
{
"plumb-mcp": {
"command": "npx",
"args": [
"-y",
"plumb-mcp"
],
"env": {
"FIGMA_TOKEN": "",
"PLUMB_SESSION_NAME": ""
}
}
}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.
- 11d ago First seen · 13 lines scan A 6d4c8bad729d
plumb-mcp is an MCP server published in the GitHub repository tathagat22/plumb-mcp (78 stars, last pushed 23d 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
figbridge
Free, local MCP bridge for Figma — HTML, CSS, Tailwind, tokens, agent handoff bundles. Runs locally from the figbridge-mcp npm package. Needs 1 environment variable to run.
imugi-ai
Design to Code — AI-powered frontend builder with visual verification. Runs locally from the imugi-ai npm package.
figma-desktop
MCP server "figma-desktop", hosted remotely at 127.0.0.1, as configured in naver/design-to-ui.
alive-analysis
Query alive-analysis history from any AI client. Tools: list, get, search, dashboard export. Runs locally from the alive-analysis-mcp npm package. Needs 1 environment variable to run.
cgraphy
Code knowledge graph over MCP: compact, token-budgeted context for AI coding agents. Runs locally from the cgraphy Python 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.