What it does
Agent Inbox gives AI agents an email inbox they can use. Per the publisher, messages the agent sends need human approval first, and inbound messages are treated as untrusted by default.
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
Agent Inbox
A real email inbox for AI agents: human-approved sends, untrusted-by-default inbound.
v0.35.5As shown on registry.modelcontextprotocol.io when we last read it