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/khalilbenaz/MDANWrote 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/khalilbenaz/mdan/mdan-method)<a href="https://agentmods.dev/mcp/khalilbenaz/mdan/mdan-method"><img src="https://agentmods.dev/badge/mcp/khalilbenaz/mdan/mdan-method/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/khalilbenaz/mdan/mdan-method"><img src="https://agentmods.dev/badge/mcp/khalilbenaz/mdan/mdan-method.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mdan-method 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
{ "mdan-method": { "command": "npx", "args": [ "-y", "mdan-method" ] } }
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 · 9 lines scan A 5853dbbb6802
mdan-method is an MCP server published in the GitHub repository khalilbenaz/MDAN (0 stars, last pushed 4d 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
live-memory
MCP server "live-memory" as configured in Cloud-Temple/live-memory. Runs locally from the live-memory Python package.
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.
mcp
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM. Runs locally from the @safeprompt.dev/mcp npm package. Needs 3 environment variables to run.
reflect-mcp
Reflection's autonomous runtime — wake, read prior state, do useful work, write back, sleep. Runs locally from the reflect-mcp Python package.
threadline-core
Self-hosted AI work-continuity memory: protocol, storage, lifecycle, and MCP server. Runs locally from the threadline-core Python package.
pensieve
MCP server "pensieve" as configured in praveen-ilangovan/pensieve. Launched with poetry run pensieve-mcp.