Scan a page for hidden prompt-injection payloads targeting AI agents.
Connect Remote server
claude mcp add --transport http cloakcheck https://cloakcheck-wheat.vercel.app/api/mcp
{
"mcpServers": {
"cloakcheck": {
"url": "https://cloakcheck-wheat.vercel.app/api/mcp"
}
}
}
{
"servers": {
"cloakcheck": {
"type": "http",
"url": "https://cloakcheck-wheat.vercel.app/api/mcp"
}
}
}
Settings > Connectors > Add custom connector
URL: https://cloakcheck-wheat.vercel.app/api/mcp
Tools 1 found in our last check
check_page_for_injectionScan a single web page for content planted to hijack an AI agent reading it -- invisible unicode (zero-width chars, the unicode 'tag' block used for steganographic prompt injection), CSS-hidden instruction text, and instruction-shaped language in alt/title/aria-label attributes…
Details
| Endpoint | https://cloakcheck-wheat.vercel.app/api/mcp (Streamable HTTP) |
| First published | 13 Sep 2026 |
| Last updated | 13 Sep 2026 |
| Registry name | app.vercel.cloakcheck-wheat/cloakcheck |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
