← Index

io.github.agenticmail/mcp

io.github.agenticmail/mcp·v0.5.59·Chat & Messaging

Real email and SMS for AI agents — send mail, receive verification codes, drive a real inbox.

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
AGENTICMAIL_API_KEY
secret

Per-agent API key issued when you create the agent. Scopes every tool call to that agent's mailbox and outbound. Either AGENTICMAIL_API_KEY or AGENTICMAIL_MASTER_KEY must be set.

AGENTICMAIL_MASTER_KEY
secret

Master key for admin operations (creating agents, listing all accounts, deleting agents). Set this when the MCP client needs admin tools; otherwise prefer the per-agent AGENTICMAIL_API_KEY.

AGENTICMAIL_API_URL

Base URL of the AgenticMail HTTP API. Defaults to http://127.0.0.1:3100 (the port the local CLI binds). Override when the API runs on a different host or port.

MCP quality score · maturity, not trust · methodology
freshness
24
completeness
10
installability
25
documentation
15
stability
5
Alternatives in Chat & Messaging