Agents with web tools
An AI Agent node that fetches and extracts live pages mid-workflow.
Get the current price of this SKU on each competitor URL in the input.
Two connections. The MCP Client Tool gives n8n’s AI Agent node the Import.io Web Scraper MCP toolset. The Webhook node starts a workflow each time an extractor run succeeds.
Node MCP Client Tool
Endpoint https://mcp.import.io/mcp
Server transport HTTP Streamable
Authentication Bearer Auth → mcp_live_...Trigger Webhook (POST) → Production URL
Import.io extractor settings → Webhooks → paste URL
Next HTTP Request → GET the run’s JSON link
Then Split Out → Postgres / Google Sheets / SlackAny public page, rendered, through managed proxies
Rendering, proxy routing, captcha handling, extraction
https://mcp.import.io/mcp
Import.io as an AI Agent tool and as a workflow trigger.
Also connects via webhooks.
An AI Agent node that fetches and extracts live pages mid-workflow.
Get the current price of this SKU on each competitor URL in the input.
Webhook in, rows out to Postgres, Sheets or Slack.
Keep the workflow on your own n8n instance and call Import.io over HTTPS.
https://mcp.import.io/mcp, HTTP Streamable transport and Bearer auth.Use the MCP Client Tool when a model decides what to fetch. Use the webhook when an extractor already runs on a schedule and the workflow should react to new data.
Signup includes 10,000 successful calls. After that it is $0.0002 per successful call. Setup requests, tool listings, malformed requests, blocked requests and failed upstream calls are never billed, and you can set a monthly spend limit that stops paid usage when reached.
Use OAuth in interactive clients that support it: the client opens a sign-in, stores the credentials and reuses them. Use an API key for scripts, servers and clients without OAuth, sent as Authorization: Bearer mcp_live_…. Keep keys out of prompts and shared config files.
importio_web_fetch, importio_render, importio_extract_data and importio_get_html, page helpers such as importio_page_text, importio_page_links and importio_search_cards, and browser actions for clicks, form input, scrolling, pagination, waits, screenshots and captcha handling. Requests can pick a proxy country and type, with bounded retries when a page blocks.
Every time a crawl run finishes successfully. Import.io POSTs to your URL with the extractor ID, total URL count and links to the run’s JSON, CSV and Excel outputs. You can view a sample payload in the extractor’s settings.
Start a Zap every time an Import.io run succeeds.
Setup 5 minWebhookA custom webhook scenario that runs on every successful extraction.
Setup 5 minWebhookStart Microsoft flows from Import.io runs.
Setup 10 minMCPLoad Import.io tools with langchain-mcp-adapters into any agent.
Setup 10 min