Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
io.github.revsmoke/promptrejectormcp
https://github.com/revsmoke/promptrejectormcp
STDIO
1 required env var
How models use it and what it is built for.
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Your API key for the service
Where to find authoritative docs and source for promptrejectormcp.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent Studio