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/larklaon/one-bad-ideaWrote 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/larklaon/one-bad-idea/not-work)<a href="https://agentmods.dev/mcp/larklaon/one-bad-idea/not-work"><img src="https://agentmods.dev/badge/mcp/larklaon/one-bad-idea/not-work.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
not-work 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 6d 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
{
"not-work": {
"url": "https://one-bad-idea.larklaon.chatgpt.site/api/mcp",
"type": "streamable-http"
}
}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.
- 6d ago First seen · 6 lines scan A cd0f248ca95a
not-work is an MCP server published in the GitHub repository larklaon/one-bad-idea (0 stars, last pushed 1mo 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
agent-readiness
Make any website agent-ready: scan it, generate llms.txt + WebMCP tool scaffolds, inject them into your project, score it, and open the fix as a PR. Runs locally from the agent-readiness npm package.
geo-optimizer
MCP server "geo-optimizer" as configured in Auriti-Labs/geo-optimizer-skill. Launched with .venv/bin/geo-mcp. Needs 1 environment variable to run.
technocore-chat
MCP server for technocore-chat: shared rooms, durable notes and rendezvous for agents, over plain HTTP. Runs locally from the technocore-mcp Python package. Needs 2 environment variables to run.
ng-blatui
MCP server "ng-blatui", hosted remotely at ngblatui.remix-it.com, as configured in anousss007/ng-blatui.
ak-docs
Human↔agent documentation bridge — deterministic handoffs, doc-site links, memory→docs, optional AgentsKit RAG/chat. Runs locally from the @agentskit/doc-bridge npm package.
doc-bridge
Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code. Runs locally from the @agentskit/doc-bridge npm package.