What it does
Prompt Sanitizer checks untrusted content for prompt injection before an agent processes it. According to the publisher, it covers web pages, emails, PDFs and tool output.
The publisher's description is the only documentation available for this entry, so details about setup and usage are not listed here.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 14 Nov 2026 · last seen 14 Nov 2026 · its page on the source
Prompt Sanitizer — prompt-injection scan for untrusted content
Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it