Skip to main content
Glama

Setup

Add the server in your client, then sign in to Famulor and approve the requested workspace permissions in the browser. Claude and ChatGPT use OAuth; there is no API key to paste into their connector settings.

Server URL: https://app.famulor.io/mcp. It runs inside the Famulor platform, so there is nothing to install or host. Your plan needs the Connect AI / MCP feature; without it the endpoint answers 403.

claude mcp add --transport http famulor https://app.famulor.io/mcp

Add the server first, then complete the browser-based OAuth flow.

Settings > Connectors > Add custom connector

https://app.famulor.io/mcp

Copy the URL, paste it into the connector dialog, and sign in when prompted.

.cursor/mcp.json

{
  "mcpServers": {
    "famulor": {
      "type": "http",
      "url": "https://app.famulor.io/mcp"
    }
  }
}

Add the server first, then complete the browser-based OAuth flow.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "famulor": {
      "serverUrl": "https://app.famulor.io/mcp"
    }
  }
}

Add the server first, then complete the browser-based OAuth flow.

.vscode/mcp.json

{
  "servers": {
    "famulor": {
      "type": "http",
      "url": "https://app.famulor.io/mcp"
    }
  }
}

Add the server first, then complete the browser-based OAuth flow.

Cline extension > MCP Servers > Configure

{
  "mcpServers": {
    "famulor": {
      "url": "https://app.famulor.io/mcp"
    }
  }
}

Add the server first, then complete the browser-based OAuth flow.

~/.continue/config.yaml

mcpServers:
  - name: famulor
    type: streamable-http
    url: "https://app.famulor.io/mcp"

Add the server first, then complete the browser-based OAuth flow.

openclaw mcp add famulor --url https://app.famulor.io/mcp --transport streamable-http --auth oauth
openclaw mcp login famulor

Or in ~/.openclaw/openclaw.json:

{
  "mcp": {
    "servers": {
      "famulor": {
        "url": "https://app.famulor.io/mcp",
        "transport": "streamable-http",
        "auth": "oauth"
      }
    }
  }
}

Tip: there is also a ready-made Famulor skill — openclaw skills install famulor-skill.

hermes mcp add famulor --url https://app.famulor.io/mcp
hermes mcp login famulor

Or in ~/.hermes/config.yaml:

mcp_servers:
  famulor:
    url: "https://app.famulor.io/mcp"
    auth: oauth

Apply in-session with /reload-mcp.

~/.config/zed/settings.json

{
  "context_servers": {
    "famulor": {
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://app.famulor.io/mcp"
      ],
      "command": "npx"
    }
  }
}

Add the server first, then complete the browser-based OAuth flow.


Related MCP server: Smallest MCP Server

What you can do

Once connected, your AI assistant discovers the current public tool catalog directly from Famulor. The catalog covers, among other areas:

Assistants — create, update, delete AI voice agents · list voices, languages, LLM/multimodal models, TTS/STT providers · toggle inbound and conversation-ended webhooks

History & calls — inspect cross-channel history and transcripts · make and manage calls

Campaigns — create campaigns, manage retry rules and allowed-hours windows · start, stop and delete

Audience — manage contacts, tags, segments, suppression and campaign membership

Knowledge bases — create knowledge bases · upload website-scraped documents · update / delete

Telephony — phone numbers, number verification, assignments and SIP trunks

Messaging & email — WhatsApp, Instagram, Messenger, Telegram, Slack, Teams, Discord, Google Chat, X, helpdesk and email conversation workflows

WhatsApp — list senders and templates · check 24h session window · send template or freeform messages

Automations & operations — flows, routines, dashboards, integrations, webhooks, booking, workspace settings and account administration

Ask the assistant in plain English, e.g. "Create a German sales assistant using GPT-4.1-mini and the Susi voice", "Start campaign #42 and add these 50 leads", "Show me all calls today where the goal wasn't reached."


How auth works

The endpoint implements MCP OAuth discovery, authorization code with PKCE, dynamic client registration and Client ID Metadata Documents. Your MCP client opens Famulor in a browser, where you sign in on app.famulor.io, choose a workspace and approve the requested permissions.

Server-to-server clients can send an API key instead: create one under Settings > API & MCP on app.famulor.io and pass it as Authorization: Bearer fam_…. Claude and ChatGPT connectors always use OAuth.

Full tool catalog and scopes: docs.famulor.io/mcp/tools-and-scopes


Famulor 1.0 (app.famulor.de)

This MCP server works with workspaces on the Famulor platform at app.famulor.io. Famulor 1.0 (app.famulor.de) stays available; to bring assistants, tools, knowledge, campaigns, automations and your own telephony over, use Migrate from Famulor 1.0.


What is in this repository

The server itself runs inside the Famulor platform. This repository holds what clients and directories need to find it:

File

Purpose

mcp.json, .plugin/plugin.json

Client and plugin configuration pointing at https://app.famulor.io/mcp

server.json

Entry in the official MCP Registry (io.famulor/famulor-mcp, remote only)

glama.json

Glama ownership claim

SUBMISSIONS.md, submissions/, chatgpt-app-submission.json

Directory submission material

assets/

Logos

The earlier self-hosted server and its npm package famulor-mcp are retired.


License

MIT

Related MCP Connectors

Related MCP Servers