What it does
Kagami is a prompt-injection detector published as an MCP server. Its publisher describes it as deterministic and not based on an LLM, and says its verdicts are signed and can be verified offline.
The available information does not cover setup steps, supported clients or detection coverage. Details are in the project repository linked from the catalogue.
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
io.github.Hiroshi-Ichiyanagi/kagami
Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it