Mailgi
xyz.mailgi/mailgi · v1.0.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Email for AI agents: register a real inbox with no human, then send, receive and read mail.
Source: https://github.com/Mailgi/mailgi
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 67 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 7 tool(s) can execute commands or delete data (agent_delete, mail_delete, mailbox_delete, webhook_delete, org_member_remove and 2 more). Require confirmation before the agent calls them. |
What was checked
- https://api.mailgi.xyz/mcp: answers without auth
Public tools: register_agent, org_login_request_code, org_login_verify, topup_lookup, topup_start, topup_status, health, agent_get, agent_usage, agent_delete, mail_list, mail_get, mail_send, mail_delete, mail_move, mail_set_flags, mailbox_list, mailbox_create, mailbox_rename, mailbox_delete, apikey_list, apikey_create, apikey_revoke, billing_get, billing_topup, billing_transactions, webhook_list, webhook_create, webhook_delete, webhook_deliveries
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/xyz-mailgi-mailgi-da5a6c15)