Home > Browse > AI Infrastructure > CallMCP

CallMCP

CallMCP is an AI-powered AI Infrastructure tool — A phone call server that lets AI agents place and answer real calls, text, email and WhatsApp via KaiCalls. Best for: AI Infrastructure. Pricing: Freemium (GateOnAI Score: 60/100).

A phone call server that lets AI agents place and answer real calls, text, email and WhatsApp via KaiCalls.

FreemiumLive

CallMCP is a phone‑call Model Context Protocol (MCP) server that lets AI agents place and receive real phone calls, join Zoom, Meet and Teams meetings, handle SMS, email and WhatsApp, and trigger webhooks—all through a single integration key. The platform provides over 180 tools, so an agent can ask Claude or ChatGPT to call a dentist, order pizza, join a meeting and return a summary, or manage inbound texts and voicemails with owner approval checks for consent, calling hours and do‑not‑call rules. Integration options include Claude Desktop, ChatGPT MCP‑capable apps, Cursor, TypeScript or Python SDKs, REST/OpenAPI, and plain HTTPS webhooks, covering phone calls, meetings, SMS, email campaigns, web chat and upcoming iMessage/RCS support. The service reports real‑time call status, provides transcripts, signed webhooks and an audit log for each action.

Summary written from CallMCP's own website on 14 Nov 2026. Check the vendor's website for current details.

Visit CallMCP

MCP server

CallMCP has an MCP server listed in the Official MCP Registry (ai.callmcp/server). AI assistants and code editors that support MCP can use CallMCP directly. Endpoint: https://callmcp.ai/mcp.

GateOnAI has not tested this server. Check the provider's documentation before you connect it.

How to evaluate CallMCP before you buy

What GateOnAI has on record

Questions to ask the vendor

  1. Will you sign a GDPR data processing agreement (Article 28) and share your list of sub-processors?
  2. Where is our data stored and processed, and is it used to train your models?
  3. What does the free plan include, and what does the plan we need cost per user?
  4. Can we export all our data, and how is it deleted when we cancel?
  5. (AI Infrastructure) Are our prompts, files or fine-tuning data used to train your models, and can we opt out in writing?
  6. (AI Infrastructure) In which regions are our data and model calls processed, and what uptime and rate limits apply to our plan?

Full checklist: 43 questions to ask an AI vendor · Alternatives to CallMCP · Compare CallMCP with Groq

More AI Infrastructure Tools

May Connect With

Tools whose input/output tags match those of CallMCP (the tags are assigned automatically and the connections are not tested):

Find similar tools | Browse all AI prompts