MCP X-RAY · a SecureAI-Scan instrument
source →
Before you run a stranger's MCP server

See what's hidden in a tool description before it runs.

Paste a tool description, an .mcp.json, or the server code you found on GitHub. This checks it for the exact patterns behind real incidents — hidden Unicode, instructions aimed at the agent instead of you, and known-malicious packages — entirely in your browser.

Paste content to examine
Nothing you paste leaves this page.

What this instrument looks for

The same three checks that ship in the SecureAI-Scan CLI — reused here so you can run them before you've even cloned anything.

MCP007

Invisible Unicode

Zero-width, bidirectional, and tag-block characters that hide text from your eyes while a model still reads it.

MCP008

Injection phrasing

Instructions aimed at the agent, not you — "ignore previous instructions," concealment from the user, reads of ~/.ssh, exfil to a URL.

DEP003

Known-bad packages

Checked against documented incidents — the postmark-mcp backdoor, published CVEs — not guesswork.