Manage AI voice agents, calls, SMS, contacts, and phone numbers via Magpipe.
Magpipe MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Manage AI voice agents, calls, SMS, contacts, and phone numbers via Magpipe.
Magpipe is a conversational platform that manages SMS/Text messages, WhatsApp, Phone Calls, Email, and Web Chat — with an AI agent on every channel and a signed webhook API for piping conversations into your own systems. Built with vanilla JavaScript, Supabase, CPaaS (SignalWire + Meta WhatsApp Cloud API), and LiveKit.
Once Magpipe is connected, these are the calls the assistant has available:
Prerequisites — The Prerequisites tool exposed by this serverInstallation — 1. Clone the repository bash git clone cd patIntegrations — HubSpot (CRM), Google Workspace (Calendar, Gmail), Cal.com (booking), Apollo.io (contact enrichment), and Slack (notifications). Native toolBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
You will need 8 environment variables: SUPABASE_ACCESS_TOKEN, VITE_SUPABASE_URL, VITE_SUPABASE_ANON_KEY, SUPABASE_SERVICE_ROLE_KEY, SIGNALWIRE_PROJECT_ID, SIGNALWIRE_API_TOKEN, SIGNALWIRE_SPACE_URL, LIVEKIT_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of team communication servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Magpipe's toolset — Prerequisites, Installation, Integrations — is a fair guide to whether it matches your workflow. It is maintained by elagerway; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Prerequisites | The Prerequisites tool exposed by this server. |
| Installation | 1. **Clone the repository** bash git clone <repo-url> cd pat |
| Integrations | HubSpot (CRM), Google Workspace (Calendar, Gmail), Cal.com (booking), Apollo.io (contact enrichment), and Slack (notifications). Native tool execution via the agent chat interface. |
{
"mcpServers": {
"magpipe": {
"command": "npx",
"args": ["-y", "supabase"],
"env": {
"SUPABASE_ACCESS_TOKEN": "your-value",
"VITE_SUPABASE_URL": "your-value",
"VITE_SUPABASE_ANON_KEY": "your-value",
"SUPABASE_SERVICE_ROLE_KEY": "your-value",
"SIGNALWIRE_PROJECT_ID": "your-value",
"SIGNALWIRE_API_TOKEN": "your-value",
"SIGNALWIRE_SPACE_URL": "your-value",
"LIVEKIT_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| SUPABASE_ACCESS_TOKEN | Credential the server authenticates with. | Yes |
| VITE_SUPABASE_URL | Endpoint or connection string the server talks to. | Yes |
| VITE_SUPABASE_ANON_KEY | Credential the server authenticates with. | Yes |
| SUPABASE_SERVICE_ROLE_KEY | Credential the server authenticates with. | Yes |
| SIGNALWIRE_PROJECT_ID | Configuration value read at startup. | Optional |
| SIGNALWIRE_API_TOKEN | Credential the server authenticates with. | Yes |
| SIGNALWIRE_SPACE_URL | Endpoint or connection string the server talks to. | Yes |
| LIVEKIT_URL | Endpoint or connection string the server talks to. | Yes |
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Inbox intelligence — search, read, draft and send Gmail through your assistant with OAuth auto-setup.
Read and write Jira, Confluence, Bitbucket, JSM and Compass from your AI client — with your own permissions.
Read and send Telegram messages through your assistant — chats, channels and history via the client API.
Enables Discord bot integration with Model Context Protocol (MCP) compatible applications like Claude Desktop.
Exposes REST APIs defined by OpenAPI specifications as Model Context Protocol (MCP) tools, facilitating seamless integration into MCP-based workflows.