Skip to content

Claude Code MalwareTracker Document Malware & AI Safety Scanner Prompt/audit_untrusted_document

How to: Claude Code MalwareTracker Document Malware & AI Safety Scanner audit_untrusted_document

client:Claude Code transport:streamable-http prompt:audit_untrusted_document

Add MalwareTracker Document Malware & AI Safety Scanner to Claude Code

  1. 01

    Run this in your project directory.

claude mcp add --transport http mcp https://api.malwaretracker.com/mcp
  1. 02

    Restart your session so the server is picked up.

  2. 03

    audit_untrusted_document is surfaced as a slash command — type / and it is in the list. Unlike a tool, you invoke it deliberately — Claude Code will not call it for you.

  3. 04

    If it does not appear, check that MalwareTracker Document Malware & AI Safety Scanner is connected and that you are looking at its prompts rather than its tools.

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

Set these first

MalwareTracker Document Malware & AI Safety Scanner will not start until these are set, so it never reaches Claude Code.

  • MALWARETRACKER_API_KEY

Same prompt, other clients

Read from the server itself, by connecting to it and calling prompts/list on 14 November 2026. A listing does not declare its prompts, so asking is the only way to know them, and this is what the server actually offers rather than what its listing claims. Names only are stored; connect the server for each prompt's arguments.