What it does
Relevant when an AI agent composes or sends email and each message should be checked before it leaves. The publisher describes the outcome as one of three verdicts, allow, review or block, with the reasons given alongside. Setup and running requirements are not described in the available information.
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
SendGuard
Check an email before your AI agent sends it: allow, review or block with reasons.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it