What it does
Lovec is an MCP server that screens untrusted text for prompt-injection attempts before that text is passed to a large language model. It handles Russian and English input. The source describes it only as a detector and does not list its outputs or detection method.
It fits workflows where an LLM receives text from sources that cannot be fully trusted, so the text can be checked first. Running it requires a key from lovec.tech, which the user must supply.
Limitations and requirements
Requires the user's own API key from lovec.tech (bring your own key).
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
Lovec
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
v0.1.2As shown on registry.modelcontextprotocol.io when we last read it