ai.sendraven/mcp
ai.sendraven/mcp · v0.4.35 · 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 infrastructure for AI agents: send, read replies as threads, campaigns, per-key limits.
Source: https://github.com/CommonNinja/sendraven-mcp-server
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 72 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 5 tool(s) can execute commands or delete data (remove_suppression, delete_media, delete_automation, remove_from_audience, delete_contact). Require confirmation before the agent calls them. |
What was checked
- https://mcp.sendraven.ai/mcp: answers without auth
- npm: @sendraven/mcp@0.4.35 (static checks only; code not executed)
Public tools: send_email, list_emails, get_email, cancel_scheduled_email, update_email_tags, list_sending_domains, add_sending_domain, verify_sending_domain, set_utm_tags, list_suppressions, add_suppression, remove_suppression, create_broadcast, get_broadcast, get_broadcast_metrics, list_broadcasts, preview_broadcast, send_broadcast, pick_broadcast_winner, resume_broadcast, list_threads, get_thread, reply_to_message, mark_thread_handled, list_templates, render_template, send_template_email, save_template, list_media, upload_media
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/ai-sendraven-mcp-862e0a98)