What it does
The server runs prompt injection and system-prompt extraction tests against LLM agents. It is listed under testing and offers a free sample set of eight probes.
It suits developers who want to check how an LLM agent responds to prompt injection attempts or attempts to extract its system prompt. The publisher's description covers only these tests and the free sample, so no further details are given 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 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Prompt Injection Detector
Prompt injection and system-prompt extraction testing for LLM agents. Free 8-probe sample.
v1.1.0As shown on registry.modelcontextprotocol.io when we last read it