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.
npx skills add unrelated-ai/mcp-gateway --skill unrelated-toolsgit clone --depth 1 https://github.com/unrelated-ai/mcp-gatewayWrote 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/skills/unrelated-ai/mcp-gateway/unrelated-tools)<a href="https://agentmods.dev/skills/unrelated-ai/mcp-gateway/unrelated-tools"><img src="https://agentmods.dev/badge/skills/unrelated-ai/mcp-gateway/unrelated-tools/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/skills/unrelated-ai/mcp-gateway/unrelated-tools"><img src="https://agentmods.dev/badge/skills/unrelated-ai/mcp-gateway/unrelated-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.00276 |
| Opus 5.5 | $0.00026 | $0.00110 |
| Sonnet 5.5 | $0.00013 | $0.00055 |
| Haiku 4.5 | $0.00006 | $0.00028 |
Grade A, and why
unrelated-tools 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
Use Unrelated Gateway tools
- Search before calling:
unrelated --json tools search "describe the intended outcome" - Use the returned stable
toolRef. Rununrelated --json tools describe <toolRef>only when the search result lacks required schema detail. - Call exactly one tool with JSON input:
unrelated --json tools call <toolRef> --input '{"key":"value"}' - Inspect the complete JSON result before deciding the next action.
Never print, request, or place credentials in command arguments. Authentication belongs to unrelated auth login or UNRELATED_TOKEN in managed non-interactive environments.
Before a tool can delete, publish, send, purchase, or otherwise cause an external side effect, follow the host agent's confirmation policy and ask the user when approval is required. Do not bypass confirmation with --yes.
Do not invent tool references or parameters. Search again when a reference is missing or stale.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 24 lines · 64 tokens per session scan A 6a20c582e7af
unrelated-tools is a skill published in the GitHub repository unrelated-ai/mcp-gateway (26 stars, last pushed 5d ago), licensed MIT. It adds 64 tokens to every session and 276 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-05.
Other skills, from other repositories
webmcp-nexus
A coding guide for adding WebMCP tools to JavaScript or TypeScript projects. WebMCP lets AI agents call selected application functions through a standard interface.
manage-lounge-history
Review, correct or delete a signed-in user's logged visits and reviews. Requires OAuth with the write scope.
list-lounge-brand-locations
List all Priority Pass, Capital One, Centurion, Chase Sapphire, Plaza Premium, LoungeKey or DragonPass lounges, grouped by country and airport.
lounge-tool-best-practice
Rules that stop the common failures: guessed slugs, missing arguments, repeated searches and rate limits.
youtube-transcripts
Read and search YouTube videos through VidWords. Use when the user supplies a YouTube URL, a bare 11-character video id, a youtu.be or Shorts link, or a channel handle, and wants any of: the transcript or subtitles (TXT/SRT/VTT), what a video says about a topic, a quote with a citable timestamp, only the words spoken…
check-lounge-access
Work out whether a specific credit card, membership, airline status or day pass gets you into a given lounge.