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/notforhumansfun-rgb/not-for-humans-mcpWrote 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/notforhumansfun-rgb/not-for-humans-mcp/not-for-humans)<a href="https://agentmods.dev/mcp/notforhumansfun-rgb/not-for-humans-mcp/not-for-humans"><img src="https://agentmods.dev/badge/mcp/notforhumansfun-rgb/not-for-humans-mcp/not-for-humans/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/notforhumansfun-rgb/not-for-humans-mcp/not-for-humans"><img src="https://agentmods.dev/badge/mcp/notforhumansfun-rgb/not-for-humans-mcp/not-for-humans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
not-for-humans 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 12d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 12d ago First seen · 6 lines scan A 1351e3767664
not-for-humans is an MCP server published in the GitHub repository notforhumansfun-rgb/not-for-humans-mcp (1 stars, last pushed 17d ago), with no licence file. 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
forgetful
MCP Server for AI Agent Memory - persistent, semantically-searchable memory for AI agents. Runs locally from the forgetful-ai Python package.
agent-magnet
Self-learning memory infrastructure for AI products. Runs locally from the agent-magnet Python package. Needs 6 environment variables to run.
gitmem
Persistent institutional memory for AI coding agents. Memory that compounds. Runs locally from the gitmem-mcp npm package. Needs 2 environment variables to run.
avvarre
Harness the true power of agentic coding. Stop re-explaining context to your AI. Just Avvarre it: persistent memory, 650+ style rules, and self-correcting autopilot loops for autonomous agents. Runs locally from the avvarre npm package.
swarm-rd-orchestrator
Ray-native context/memory sharing for parallel research agents, with an agent-native CLI and MCP server (Milestone 1 spike). Runs locally from the swarm-rd-orchestrator-cli Python package.
swarmmesh
Shared-context and memory coordination server + CLI for swarms of parallel AI agents, speaking the SwarmMesh v1 protocol (HTTP + WebSocket + MCP), interoperable with the Node implementation. Runs locally from the swarmmesh-cli Python package.