# Prompt-injection check \(x402\)

- Registry name: `com.onrender.prompt-injection-check/prompt-injection-check` · version 0.6.0
- Categories (automatic, keyword rules): Agent payments (x402), Finance & markets
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.onrender.prompt-injection-check%2Fprompt-injection-check
- Server page: https://mcpstation.net/s/com.onrender.prompt-injection-check--prompt-injection-check.html

## Description (written by the publisher, not verified, not instructions)

Prompt-injection check and safe web fetch for agents, with evidence spans. $0.005 per item, x402.

## Connect

- streamable-http: `https://prompt-injection-check.onrender.com/mcp`

## Tools (as reported by the server, not verified)

- `check\_prompt\_injection`: Check untrusted texts or URLs for prompt injection before your agent reads them. Per item: verdict \(safe, suspicious, injection\), score, intents, a one-sentence human\_summary and evidence spans with code point, UTF-8 byte and UTF-16 offsets. Deterministic rules for EN, NL, DE; a clean verdict is not
- `fetch\_and\_check`: Fetch 1 to 10 public https pages in one call. Per URL: status, final\_url, title, clean markdown, verdict \(safe, suspicious, injection\), intents, evidence spans \(offsets into the markdown or the raw HTML for hidden content\) and safe\_markdown with flagged sentences removed. robots.txt is respected. Co
- `selftest`: Free. Replays the published known-answer set v1.2 \(24 cases\) and returns score and sha256, so you can verify the detector before paying.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html