Connect an AI assistant to the Ringg AI MCP server

There are two ways in, and the client decides which one you use.

Before you start

A workspace API key

Both methods need it; the owner generates it under Settings → API key.

Pick your client

Testing and disconnecting, shared by all clients, follow the tabs.

Method	Who uses it	What you do
OAuth sign-in	Claude.ai, Claude Desktop, ChatGPT connectors	Add `https://mcp.ringg.ai/mcp` and sign in on the Ringg page the client opens. The client gets its own token, never your key.
API key as bearer token	Claude Code, Cursor, Codex CLI, custom agents, scripts	Send `Authorization: Bearer <RINGG_API_KEY>` on every request. No sign-in.

Claude.ai / Desktop
ChatGPT
Claude Code
Cursor & JSON-configured clients
Your own agent (Python)

Add the connector

Open Settings → Connectors → Add custom connector. Name it Ringg AI and set the URL to:

https://mcp.ringg.ai/mcp

Claude detects the server’s settings automatically. Leave Authentication on Always required and OAuth client on No client ID — register one automatically. Click Add.

Connect

Click Connect on the Ringg AI row. A Ringg sign-in page opens in a new tab, naming the application (Claude) and where it will send you back (claude.ai). Paste your API key and click Allow access.

Verify

Back in Claude, the connector shows a tick. Ask “What’s in my Ringg AI workspace?” The first tool call asks for permission; choose Allow, or Always allow for read-only tools.

Claude answers with your agents, numbers and credits.

Prompts and resources appear under the + menu in the chat, for example the launch_first_call playbook, or ringg://agents to attach your agent list as context.

Enable developer mode

Open Settings → Connectors → Advanced and turn on Developer mode.

Add the MCP server

Choose Create, name it Ringg AI, set the URL to https://mcp.ringg.ai/mcp and authentication to OAuth. Save.

Click Connect. On the Ringg page, paste your API key and click Allow access. ChatGPT registers itself with the server, so no client ID or secret is needed.

One command, no sign-in:

claude mcp add --transport http ringg https://mcp.ringg.ai/mcp \
  --header "Authorization: Bearer $RINGG_API_KEY"

Then, in a session: “Using Ringg, what agents do I have?”

The key is saved in Claude Code’s local configuration. If the machine is shared or lost, rotate the key.

Most desktop clients read a JSON file of MCP servers. For Cursor, add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "ringg": {
      "url": "https://mcp.ringg.ai/mcp",
      "headers": {
        "Authorization": "Bearer <RINGG_API_KEY>"
      }
    }
  }
}

Any client that supports Streamable HTTP with custom headers works the same way. Clients that implement MCP OAuth can be pointed at the URL instead; the server publishes what they need at /.well-known/oauth-authorization-server and /.well-known/oauth-protected-resource.

With the official MCP Python SDK:

import asyncio, os
import httpx
from mcp import ClientSession
from mcp.client.streamable_http import streamable_http_client

async def main():
    headers = {"Authorization": f"Bearer {os.environ['RINGG_API_KEY']}"}
    async with httpx.AsyncClient(headers=headers, timeout=120) as http, \
               streamable_http_client("https://mcp.ringg.ai/mcp", http_client=http) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            overview = await session.call_tool("get_account_overview", {})
            print(overview.structuredContent["workspace"]["name"])

asyncio.run(main())

get_call with wait_for_completion=true can run for minutes (up to its timeout_seconds, at most 600), so give your HTTP client a long timeout.

Test it safely

Ask for the account overview. It only reads.
Ask the client to create a test agent from a short brief.
Ask it to call your own number with that agent and wait for the transcript. Your client should ask you to confirm before dialling.

If the call fails at once with a caller-ID error, pick a number the overview marks as usable for live calls (why).

Disconnect

Remove the connector in the client’s settings, or regenerate the API key to cut off every client at once; see Revoking access. Next: the tool reference lists every tool, resource and prompt the connected client can use, with inputs and defaults.

Next steps

Tool reference

What the client can and cannot do in your workspace, and how to phrase requests.

Security and FAQ

How sign-in protects the key, what is stored and how to revoke access.

Docs MCP server

Workspace MCP server

Connect an AI assistant

Before you start

A workspace API key

Pick your client

Test it safely

Disconnect

Next steps

Tool reference

Security and FAQ

​Before you start

A workspace API key

​Pick your client

​Test it safely

​Disconnect

​Next steps

Tool reference

Security and FAQ

Before you start

Pick your client

Test it safely

Disconnect

Next steps