Website Content Crawler MCP Server

MCP wrapper that runs the apify/website-content-crawler actor for real via apify-client and returns its pages as JSON. Every call either returns crawled content or a structured error — it never reports a fake success.

What it costs

Runs bill your Apify account at the rate listed for apify/website-content-crawler — this server adds nothing on top. No token, no charge: calls return missing_token before any run starts.

Live output demo (same crawl logic, rendered): https://website-content-crawler.vercel.app

Setup

npm install
export APIFY_TOKEN=apify_api_...   # https://console.apify.com/settings/integrations
npm start                          # stdio MCP server

Tool: crawl_website

Input:

field	type	default	notes
url	string	required	http/https URL to crawl
maxPages	number	10	capped at 50
crawlerType	string	cheerio	or playwright:chrome for JS-rendered

Output envelope (same shape every call):

{
  "status": "ok",
  "run": { "id": "<apify run id>", "status": "SUCCEEDED" },
  "page_count": 3,
  "total_in_dataset": 3,
  "pages": [{ "url": "...", "title": "...", "text": "...(≤5000 chars)" }]
}

Error codes: invalid_url, missing_token, apify_auth_failed, actor_run_failed, run_not_succeeded, dataset_fetch_failed.

Smoke test

printf '%s\n' \
 '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"t","version":"0"}}}' \
 '{"jsonrpc":"2.0","method":"notifications/initialized"}' \
 '{"jsonrpc":"2.0","id":2,"method":"tools/list"}' \
 '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"crawl_website","arguments":{"url":"https://example.com"}}}' \
 | node index.js

With no APIFY_TOKEN set, request id 3 must return {"status":"error","error":{"code":"missing_token",...}} — proof the handler reaches the real Apify boundary instead of inventing a result.