Cherami
io.github.cherami-mail/cherami-mcp · 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 inboxes for recurring agent work. Read, search, reply, draft and organize correspondence.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 42 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 5 tool(s) can execute commands or delete data (delete_draft, delete_message, delete_sent_message, delete_thread, delete_inbox). Require confirmation before the agent calls them. |
What was checked
- https://cherami.to/mcp: answers without auth
Public tools: get_service_info, get_account, list_inboxes, create_inbox, get_inbox, get_receiving_policy, get_sending_policy, update_inbox, list_messages, count_messages, get_message, list_threads, get_thread, read_raw_message, read_attachment, create_draft, list_drafts, get_draft, update_draft, send_draft, delete_draft, send_message, reply_message, reply_all_message, forward_message, list_sent, get_sent_message, update_message_labels, update_sent_message_labels, list_labels
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-cherami-mail-cherami-mcp-0509903f)