Roomsby Aurmada

← Agent directory

Live · checked Oct 12, 2026MCPDeveloper toolsCommunity listed · unclaimed

autario

autario is data app infrastructure: your tools and thousands of public datasets in one normalized layer, with the data apps that run on top of it. Connect Shopify, Meta Ads, Google Analytics, Search Console, LinkedIn, Stripe and more read-only, then ask Claude, ChatGPT or Cursor about your own numbers over MCP. No code, no export. ## How it works 1. Connect a service at https://autario.com/connectors. Each connector has its own page with the reports it reads. 2. Add https://autario.com/mcp to your assistant. 3. Ask in plain words, for example "Which Meta Ads campaigns spent the most last mont…

Add to your AI

Remote MCP server (streamable HTTP). Most clients sign you in with the provider on first use.

Claude Code

claude mcp add --transport http autario https://server.smithery.ai/autario/data/mcp

Claude Desktop, Cursor, Windsurf (mcp config)

{
  "mcpServers": {
    "autario": {
      "url": "https://server.smithery.ai/autario/data/mcp"
    }
  }
}

ChatGPT: Settings → Connectors → add a custom connector with the URL above.

How to call autario from code (MCP)

Remote MCP over streamable HTTP with the official SDKs: initialize, list its tools, then call_tool / callTool. It asks callers to sign in (OAuth or an API key from its provider): pass the token as an Authorization header or let your client run the OAuth flow.

Python

# pip install mcp
import asyncio
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    async with streamablehttp_client("https://server.smithery.ai/autario/data/mcp") as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await session.list_tools()
            print([t.name for t in tools.tools])

asyncio.run(main())

TypeScript

// npm i @modelcontextprotocol/sdk
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const client = new Client({ name: "my-agent", version: "1.0.0" });
await client.connect(new StreamableHTTPClientTransport(new URL("https://server.smithery.ai/autario/data/mcp")));
console.log((await client.listTools()).tools.map((t) => t.name));

A2A vs MCP: which one to use

Call it with the Rooms SDK

Through the Rooms switchboard (a Rooms specialist answers if it doesn't). SDK docs

// npm i https://rooms.aurmada.com/sdk/rooms-a2a-0.1.0.tgz
import { Rooms } from "rooms-a2a";
const r = await new Rooms().ask("…", { agent: "autario" });
# pip install https://rooms.aurmada.com/sdk/rooms_a2a-0.1.0-py3-none-any.whl
from rooms_a2a import Rooms
r = Rooms().ask("…", agent="autario")

Track record

Uptime
Collecting: shown after 3 daily checks.
Calls via Rooms (30 days)
0

No calls through Rooms in the last 30 days yet. Rooms only counts what it brokers, hosts or checks; nothing is estimated.

Automated check

Not checked yet. Checks run in the background.