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/SunrisesIllNeverSee/agent-universeWrote 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/sunrisesillneversee/agent-universe/civitae)<a href="https://agentmods.dev/mcp/sunrisesillneversee/agent-universe/civitae"><img src="https://agentmods.dev/badge/mcp/sunrisesillneversee/agent-universe/civitae/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/sunrisesillneversee/agent-universe/civitae"><img src="https://agentmods.dev/badge/mcp/sunrisesillneversee/agent-universe/civitae.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
civitae 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 9d 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
{
"civitae": {
"command": "uvx",
"args": [
"civitae-mcp"
],
"env": {}
}
}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.
- 9d ago First seen · 9 lines scan A 8acb16de778e
civitae is an MCP server published in the GitHub repository SunrisesIllNeverSee/agent-universe (1 stars, last pushed yesterday), 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
ozon-mcp-server
MCP server for Ozon Seller API + Performance API: 151 tools for prices, promos, ads, orders, returns and finance. Runs locally from the ozon-mcp-server Python package. Needs 5 environment variables to run.
cli-market-world
mcp-name: io.github.Treevu-ai/cli-market-world - CLI Market: commerce API for AI agents. 44 curated MCP tools (76 legacy), 46 indicators, 336 verified retailers in 21 countries. MIT. Runs locally from the cli-market-world Python package. Needs 2 environment variables to run.
cli-market
mcp-name: io.github.Treevu-ai/cli-market-world - CLI Market: commerce API for AI agents. 43 MCP tools, 34 indicators, 38 verified retailers in 8 countries. MIT. Runs locally from the cli-market Python package.
governance-mcp
MCP server "governance-mcp" as configured in cirwel/unitares. Runs locally from the governance-mcp Python package.
receipts-api
MCP server "receipts-api" as configured in chf3198/receipts-api-mcp. Runs locally from the receipts-api Python package.
assurance-mcp
Read-only MCP server exposing assurance checks over a folder. Runs locally from the assurance-mcp Python package.