Hail
io.github.hail-hq/hail-mcp · v0.2.0 · 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
Run your AI assistant with real phone numbers and email inboxes. Handle calls, texts, and email.
Source: https://github.com/hail-hq/hail
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 46 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_agent). Require confirmation before the agent calls them. |
What was checked
- https://mcp.hail.so: answers without auth
Public tools: place_call, send_email, upload_email_attachment, create_file_upload, get_call, list_calls, send_sms, get_sms, list_sms, get_email, list_emails, get_email_raw, get_email_attachment, get_email_events, get_email_stats, get_events, list_agents, create_agent, route_number, route_email_domain, quote_numbers, acquire_number, list_numbers, list_number_regions, get_number, release_number, get_verification_requirements, check_verification, check_verification_documents, submit_verification
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-hail-hq-hail-mcp-afec5387)