Dialfetch MCP Server

Give your AI agent a phone: place calls, navigate IVRs, wait on hold, get structured answers.

Local serverstdio

What is the Dialfetch MCP server?

Most developer tooling work still happens through a UI a human drives. Dialfetch MCP server moves it into the conversation instead. Give your AI agent a phone: place calls, navigate IVRs, wait on hold, get structured answers.

The short version

Give it a phone number and a plain-language goal. Goal in, result out.

The tools it exposes

The server publishes 9 tools. What each one is for:

  • place_call — phone, goal, extract?, context?, disclose_ai?, from_number_id?, max_duration_minutes?, webhook_url?
  • get_call — call_id
  • wait_for_call — call_id, timeout_seconds?
  • cancel_call — call_id
  • list_calls — status?, limit?, cursor?
  • get_call_recording — call_id
  • list_phone_numbers — —
  • get_pricing — —
  • get_credit_balance — —

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Dialfetch's toolset — place_call, get_call, wait_for_call and 6 more — is a fair guide to whether it matches your workflow. It is maintained by com.dialfetch; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Dialfetch.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
place_callphone, goal, extract?, context?, disclose_ai?, from_number_id?, max_duration_minutes?, webhook_url?
get_callcall_id
wait_for_callcall_id, timeout_seconds?
cancel_callcall_id
list_callsstatus?, limit?, cursor?
get_call_recordingcall_id
list_phone_numbers
get_pricing
get_credit_balance

How to install the Dialfetch MCP server

{
  "mcpServers": {
    "dialfetch": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://app.dialfetch.com/api/mcp",
               "--header", "Authorization: Bearer df_YOUR_KEY"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Dialfetch to place call.
  • Use Dialfetch to get call.
  • Use Dialfetch to wait for call.

Frequently asked questions

It connects Dialfetch to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (place_call, get_call, wait_for_call, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Dialfetch directly.