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/madonchik123/umbrella-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/madonchik123/umbrella-mcp/umbrella-runtime-mcp)<a href="https://agentmods.dev/mcp/madonchik123/umbrella-mcp/umbrella-runtime-mcp"><img src="https://agentmods.dev/badge/mcp/madonchik123/umbrella-mcp/umbrella-runtime-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/madonchik123/umbrella-mcp/umbrella-runtime-mcp"><img src="https://agentmods.dev/badge/mcp/madonchik123/umbrella-mcp/umbrella-runtime-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
umbrella-runtime-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 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.
What it actually says
{ "umbrella-runtime-mcp": { "command": "uvx", "args": [ "umbrella-runtime-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.
- 10d ago First seen · 8 lines scan A da59fff900e6
umbrella-runtime-mcp is an MCP server published in the GitHub repository madonchik123/umbrella-mcp (3 stars, last pushed 1mo 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
fff
MCP server "fff" as configured in dmtrKovalenko/fff. Launched with ./target/release/fff-mcp.
hated-wow-mcp
MCP server for World of Warcraft addon development — 20 tools giving Claude, Cursor and any MCP client the in-game Lua API, Blizzard's shipped UI source, CVars, FileDataIDs and texture atlases, plus Lua linting, TOC/XML validation and addon scaffolding. R. Runs locally from the hated-wow-mcp npm package.
memscope-mcp
AI-native memory research MCP server for reverse engineering. Runs locally from the memscope-mcp Python package.
mlua-swarm
MCP server "mlua-swarm" as configured in ynishi/mlua-swarm. Runs in Docker (ghcr.io/ynishi/mse:0.9.2).
liquipedia-dota2-mcp
Read-only MCP server and Codex skill for Dota 2 esports data from Liquipedia. Runs locally from the liquipedia-dota2-mcp npm package.
gmod-mcp
MCP tool for Garry's Mod: RCON, Lua execution, window screenshot/control, and SFTP file management. Runs locally from the gmod-mcp npm package.