co.youraitools/injectscan

up checked 2026-11-10T23:38:04.224Z

Unclaimed · Unverified

Publisher-provided title

InjectScan

Publisher-provided description

Scan text for prompt injection: risk score, verdict, matched spans. Built by Crypto Money Maker

Summary by lookupd

Scans text, tool definitions, and public web pages for prompt injection and tool poisoning, returning a risk score and matched spans.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http injectscan https://api.youraitools.co/injectscan/mcp

Codex, remote (streamable-http)

codex mcp add injectscan --url https://api.youraitools.co/injectscan/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "injectscan": {
      "url": "https://api.youraitools.co/injectscan/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

scan_text Scans untrusted text for prompt injection before your agent reads or acts on it: web page text, emails, documents, tool results or another agent's message. Flag
scan_url Fetches a public web page and scans its visible text plus hidden HTML (comments, hidden elements, alt/aria/meta text) for prompt injection, before your agent br
scan_tools Checks MCP / function-calling tool definitions for tool poisoning (hidden instructions, data-exfiltration requests, hijack attempts in names, descriptions and s

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/co.youraitools/injectscan.svg)](https://lookupd.com/servers/co.youraitools/injectscan)