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/pete-builds/mcp-unifiWrote 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/pete-builds/mcp-unifi/unifi)<a href="https://agentmods.dev/mcp/pete-builds/mcp-unifi/unifi"><img src="https://agentmods.dev/badge/mcp/pete-builds/mcp-unifi/unifi/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/pete-builds/mcp-unifi/unifi"><img src="https://agentmods.dev/badge/mcp/pete-builds/mcp-unifi/unifi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
unifi 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
{
"unifi": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/pete-builds/mcp-unifi:0.5.1"
],
"env": {
"STUB_MODE": "true",
"UNIFI_HOST": "",
"UNIFI_API_KEY": "",
"UNIFI_SITE": "default",
"UNIFI_VERIFY_SSL": "false",
"MCP_UNIFI_CONTROLLERS_FILE": "",
"MCP_UNIFI_MODULES_ENABLED": "network",
"MCP_UNIFI_AUDIT_SINK": "file",
"MCP_UNIFI_AUDIT_PATH": "audit.jsonl"
}
}
}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 · 22 lines scan A 21d79d058dd4
unifi is an MCP server published in the GitHub repository pete-builds/mcp-unifi (22 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 2026-08-30.
Other mcp servers, from other repositories
unraid
Rust MCP server and CLI for Unraid GraphQL operations across NAS, Docker, VM, and storage workflows. Runs locally from the @dinglebear/unraid npm package. Needs 6 environment variables to run.
unraid-mcp
MCP Server for Unraid API - provides tools to interact with an Unraid server's GraphQL API. Runs locally from the unraid-mcp Python package. Needs 3 environment variables to run.
unraid-mcp
MCP Server for Unraid API - provides tools to interact with an Unraid server's GraphQL API. Runs locally from the unraid-mcp Python package. Needs 2 environment variables to run.
mnemo-mcp
Open-source MCP Server for persistent AI memory with embedded sync. Runs locally from the mnemo-mcp Python package. Needs 1 environment variable to run.
swag-mcp
MCP server "swag-mcp", hosted remotely, as configured in jmagar/swag-mcp.
mcp-phish
MCP server "mcp-phish" as configured in pete-builds/mcp-phish. Runs locally from the mcp-phish Python package.