AutomationNation data tools (via Apify) README

AutomationNation MCP server: Google Flights, Hotels, Shopping, News, Jobs, Trends, Maps leads, YouTube transcripts and more for AI agents

An MCP server with 18 data tools for Claude, ChatGPT, Cursor, VS Code and other AI agents. Each tool runs one of AutomationNation's Apify Actors on your Apify account and returns compact JSON the agent can use straight away: flight fares, hotel prices, product prices, news, jobs, search trends, local business leads, competitors' ads, YouTube transcripts, app reviews and AI-search visibility.

• Purpose-built tools: short, documented inputs (origin, destination, departure_date…) instead of raw scraper schemas, and outputs trimmed to the fields an agent needs.
• Pay per result, no subscription: usage is billed by each Actor on your Apify account (prices below). A free Apify account includes monthly credit.
• Safe by default: every run carries a spending cap of about 3x its expected cost; long runs return partial results with a run_id instead of timing out.
• Works without a token for discovery: tools are listed before you configure anything, so clients and registries can inspect them.

Try it without installing anything: add https://mcp.apify.com/?tools=automationnation/data-tools-mcp-server as a connector in Claude, ChatGPT or any remote-MCP client, sign in with Apify, and ask something like "find nonstop flights from London to New York on 12 November". Other ways to run it are under Install.

Tools

Install

No install (Claude, ChatGPT and other clients with remote MCP): add this URL as a connector and sign in with Apify:

https://mcp.apify.com/?tools=automationnation/data-tools-mcp-server

It runs the same server hosted on Apify (data-tools-mcp-server). Clients that use mcp.json can connect to https://automationnation--data-tools-mcp-server.apify.actor/mcp with the header Authorization: Bearer <APIFY_TOKEN>. Add ?tools=travel (or any toolset below) to load fewer tools.

Run it yourself: You need an Apify API token: sign up free at console.apify.com, then copy the token from Settings → API & Integrations.

MCP Registry name: io.github.retracn/automationnation-mcp.

Claude Desktop: download automationnation-mcp.mcpb (or a smaller toolset below), open it, and paste your token when asked.

Claude Code

claude mcp add automationnation -e APIFY_TOKEN=your_apify_token -- npx -y github:retracn/automationnation-mcp

Cursor, VS Code, Windsurf, Cline and other clients (mcp.json):

{
  "mcpServers": {
    "automationnation": {
      "command": "npx",
      "args": ["-y", "github:retracn/automationnation-mcp"],
      "env": { "APIFY_TOKEN": "your_apify_token", "AUTOMATIONNATION_TOOLS": "all" }
    }
  }
}

Hosted endpoint for any client with remote MCP (Streamable HTTP, nothing to install; your token goes in a header):

{
  "mcpServers": {
    "automationnation": {
      "url": "https://automationnation--data-tools-mcp-server.apify.actor/mcp",
      "headers": { "Authorization": "Bearer your_apify_token" }
    }
  }
}

Open WebUI: Admin Panel → Settings → External Tools → +, type MCP (Streamable HTTP), URL https://automationnation--data-tools-mcp-server.apify.actor/mcp, auth Bearer with your Apify token. Prefer single tools? See open-webui-tools.

LibreChat (librechat.yaml):

mcpServers:
  automationnation:
    type: streamable-http
    url: https://automationnation--data-tools-mcp-server.apify.actor/mcp
    headers:
      Authorization: "Bearer your_apify_token"

Smithery: npx -y @smithery/cli mcp add automationnation/data-tools

Self-hosted over HTTP (one deployment serves many users; each client sends its own token as Authorization: Bearer <APIFY_TOKEN>):

npx -y github:retracn/automationnation-mcp --http --port 8080      # http://localhost:8080/mcp
docker build -t automationnation-mcp . && docker run -p 8080:8080 automationnation-mcp --http

Toolsets

Load only what you need with AUTOMATIONNATION_TOOLS (or --tools): a comma-separated list of toolsets or tool names. Fewer tools keep the agent's context small.

How it works

1. The agent calls a tool, for example search_flights with {"origin": "JFK", "destination": "LHR", "departure_date": "2026-11-12"}.
2. The server starts the matching Actor through the Apify API with your token and a spending cap (maxTotalChargeUsd), and sends progress updates while it runs.
3. Most tools finish in 5–30 seconds; lead searches take 1–3 minutes. The server waits up to 4 minutes (AUTOMATIONNATION_WAIT_SECS), then returns a one-line summary, the Apify run link and the results as compact JSON.
4. If a run is still going, the tool returns what is ready plus a run_id; get_run_results fetches the rest.

Your token is only sent to api.apify.com. Runs, datasets and spend are visible in your Apify Console.

No install: Apify's hosted MCP endpoints

Every Actor is also available on Apify's hosted MCP server with OAuth sign-in. These listings are in the official MCP Registry:

Use the URL in any client with remote MCP support; clients with MCP OAuth (Claude, ChatGPT) sign in with Apify, others send Authorization: Bearer <APIFY_TOKEN>.

Development

npm install
npm test                      # stdio end-to-end tests against a mock Apify API
node scripts/build.mjs        # dist/index.js plus one .mcpb bundle per toolset

servers/*/server.json are the MCP Registry listings; the GitHub Actions workflow publishes them when they change.

Related: drop-in packages for broken libraries

The same Actors also power open-source drop-in replacements. Change one import and keep your code:

More: guides and examples · all AutomationNation Actors

MIT licensed.