Model Context Protocol

Run Vomyra from Claude

Claude connects to Vomyra over a custom connector. Once it's linked, you can build assistants, place calls and read transcripts by asking Claude in plain English — no dashboard, no code.

Endpoint https://console.vomyra.com/mcp · Streamable HTTP · OAuth

Setup

The short version

About 4 steps. The full guide has the screenshots and the edge cases.

  1. 1

    Open Claude's connector settings

    In Claude.ai, go to Settings → Connectors and choose “Add custom connector”.

  2. 2

    Point it at Vomyra

    Name it “Vomyra” and enter https://console.vomyra.com/mcp as the MCP server URL.

  3. 3

    Sign in with OAuth

    Pick OAuth when prompted, complete the sign-in popup, and grant the mcp:tools permission — that's what gives Claude access to your assistants, tools, calls and numbers.

  4. 4

    Check it worked

    Ask Claude “List my Vomyra assistants”. If they come back, you're connected.

Verify

Try saying

Once Claude is connected, these prove it's working.

  • List my Vomyra assistants
  • Create an assistant that books appointments for my clinic
  • Call +91… and ask about the order status, then summarise the transcript

Worth knowing

  • Claude Desktop works too — add Vomyra to claude_desktop_config.json and restart; the OAuth flow opens in your browser on first use.
  • Access tokens refresh automatically every hour. Refresh tokens last 30 days.
Capabilities

What Claude can reach

24 actions in total, across four areas of your Vomyra account.

Assistants10

Create, configure and manage voice assistants and their settings.

Tools6

Build and control the actions your assistants can perform on a call.

Calls5

Place outbound calls and pull conversation transcripts.

Numbers3

Inspect phone numbers and how calls route to your assistants.

See every action in the docs