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/unravel-team/thing-cliWrote 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/unravel-team/thing-cli/thing)<a href="https://agentmods.dev/mcp/unravel-team/thing-cli/thing"><img src="https://agentmods.dev/badge/mcp/unravel-team/thing-cli/thing/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/unravel-team/thing-cli/thing"><img src="https://agentmods.dev/badge/mcp/unravel-team/thing-cli/thing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
thing 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 1mo 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
{
"thing": {
"command": "npx",
"args": [
"-y",
"@unravel-tech/thing",
"mcp"
],
"env": {
"THING_TOKEN": "",
"THING_SERVER": ""
}
}
}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.
- 1mo ago First seen · 14 lines scan A bc4872f6621d
thing is an MCP server published in the GitHub repository unravel-team/thing-cli (0 stars, last pushed 2d 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
searchts
The missing layer between AI and the web. Open-source escalating unlocker (browser-fingerprinted fetch -> JS-render relay -> stealth browser) for read, keyless multi-provider search with rank fusion, subtitles-first video transcribe, and on-demand asset/design-inspiration grab (palette/fonts/assets through the same…
coverctl
MCP server "coverctl" as configured in klarlabs-studio/coverctl. Launched with https://github.com/klarlabs-studio/coverctl/releases/download/v1.20.0/coverctl-m.
truthroute
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP. Runs locally from the truthroute-cli npm package.
artifacty
Local artifact exchange for heterogeneous LLM agents via HTTP and MCP. Runs locally from the artifacty npm package.
sssnack
Agent-native CLI and skill for visual collaboration, Scout discovery, optional signatures, an open ledger, daily ROOT challenges, and publishing on sssnack.com. Runs locally from the sssnack npm package.
microsoft-learn
MCP server "microsoft-learn", hosted remotely at learn.microsoft.com, as configured in microsoft/Build-CLI.