CallMCP — Phone Call MCP Server
ai.callmcp/server · v0.1.5 · 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
Phone call MCP server: AI agents place and answer real calls, text, email and WhatsApp via KaiCalls.
Source: https://github.com/CallMCP/callmcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 213 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 4 tool(s) can execute commands or delete data (remove_own_caller_id, delete_webhook, create_eval, run_eval). Require confirmation before the agent calls them. |
What was checked
- https://callmcp.ai/mcp: answers without auth
- npm: @callmcp/server@0.1.5 (static checks only; code not executed)
Public tools: request_human_approval, connect_agent, get_agent_connection, disconnect_agent, get_lsa_account_report, get_lsa_setup, sync_lsa, list_lsa_leads, get_lsa_conversations, get_lsa_report, send_lsa_reply, rate_lsa_lead, get_callrail, manage_callrail, get_nimbata, manage_nimbata, agency_profile_bootstrap, agency_profile_update, agency_profile_invite, agency_profile_accept_invite, agency_profile_revoke_invite, agency_profile_assign, agency_profile_unassign, agency_profile_revoke_member, agency_profile_issue_key, agency_offer_save, agency_offer_preview, agency_offer_publish, agency_offer_archive, agency_enrollment_start_self_service
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/ai-callmcp-server-58acbd16)