Prompt Sanitizer — prompt-injection scan for untrusted content
Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.
Open the source (opens github.com) https://github.com/daoudandiaye98-alt/mcp-prompt-sanitizer
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
What it is
MCP servers from com.oroboros-design.angel.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Remote endpoint (streamable-http)
https://angel.oroboros-design.com/mcp/prompt-sanitizer
From the server's entry in the official MCP Registry
Related
-
prompt-guard-mcp
MCP serversScans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
-
Sanity
MCP serversGives AI agents direct access to your Sanity projects and guidance for working with them
-
CanaryGuard 402
MCP serversDeterministic prompt-injection detection & sanitization for AI agents via x402 on Base.
-
mcp-sanity-images
MCP serversMCP server for uploading local images to Sanity CMS
mcp-sanity-images@0.3.7 -
Quant math derivation sanity check — Atom
MCP serversQuant math derivation sanity check: declared mathematical derivation record checked per call.
-
Sanity Check — Technical Architecture Review
MCP serversAutomated architecture sanity check: 19 rule-cited checks, verdict report. Paid runs US$99.