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/robotostudio/turbo-start-sanityWrote 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/robotostudio/turbo-start-sanity/turbo-start-sanity-kb)<a href="https://agentmods.dev/mcp/robotostudio/turbo-start-sanity/turbo-start-sanity-kb"><img src="https://agentmods.dev/badge/mcp/robotostudio/turbo-start-sanity/turbo-start-sanity-kb/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/robotostudio/turbo-start-sanity/turbo-start-sanity-kb"><img src="https://agentmods.dev/badge/mcp/robotostudio/turbo-start-sanity/turbo-start-sanity-kb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
turbo-start-sanity-kb 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 25d 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
{
"turbo-start-sanity-kb": {
"type": "http",
"url": "${SANITY_CONTEXT_ENDPOINT}",
"headers": {
"Authorization": "Bearer ${SANITY_CONTEXT_TOKEN}"
}
}
}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.
- 25d ago First seen · 9 lines scan A 7109147d711b
turbo-start-sanity-kb is an MCP server published in the GitHub repository robotostudio/turbo-start-sanity (183 stars, last pushed today), 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 2026-09-22.
Other mcp servers, from other repositories
mcp
MCP server for UI Beats. Let your coding agent search, read and install animated React components. Runs locally from the @uibeats/mcp npm package.
todox
MCP server "todox", hosted remotely at www.todox.dev, as configured in beydemirfurkan/todox.
htmlradar
MCP server for HTMLRadar — publish the HTML your agent just wrote as a tracked link, then ask whether the recipient read it. Runs locally from the htmlradar-mcp npm package. Needs 1 environment variable to run.
share
Publish HTML as a tracked link and see who opened it and which sections they read. Runs locally from the htmlradar-mcp npm package. Needs 1 environment variable to run.
playwright
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
cookie-jar-local
MCP server "cookie-jar-local", hosted remotely at localhost, as configured in ketankshukla/learn-mcp-5-year-old.