An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Importio Web Data Extraction to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn any website into structured data through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Import.io.

  1. 01

    Account usage

    Checks your Import.io API credit consumption. Use this to see how many credits remain in your monthly cycle.

  2. 02

    Get crawl data

    Retrieves the final JSON output from a finished crawl job. This is how you get the data your agent collected.

  3. 03

    Get crawl status

    Monitors the progress of an active crawl. It reports on pages processed, success rates, and the current state of the job.

  4. 04

    Get extractor status

    Tracks the state of a specific extraction run. It tells you if a run is still active, completed, or failed.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Import.io.

  1. 05

    Start crawl

    Triggers a large-scale crawl across multiple web pages. This is for high-volume data collection tasks.

  2. 06

    Get extractor data

    Fetches the structured JSON data from a completed extractor run. It only works once the extraction is finished.

  3. 07

    List extractors

    Lists all the extractors configured in your Import.io account. Use this to find the right ID to run.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Import.io.

  1. 08

    Download csv

    Downloads extraction results as CSV text. It provides the first 1000 characters, which is perfect for quick spreadsheet work.

  2. 09

    Run magic API

    Runs the automated Magic API against a specific URL. This is the fastest way to pull data from a site without a pre-built extractor.

  3. 10

    Run extractor

    Starts an asynchronous extraction run for a specific URL. It returns a run ID so you can check back later for the results.

Real work

What teams actually run

01

Competitor Pricing Monitoring

An analyst tells the agent to run an extractor on a competitor's site to track price changes.

02

Rapid Site Exploration

A researcher uses the Magic API to quickly pull a table of data from a new website.

03

Large Scale Market Audits

A team starts a bulk crawl to gather data from thousands of product pages simultaneously.

04

Data Pipeline Automation

A developer uses the agent to fetch structured JSON and feed it into a downstream application.

Automate a task

Put Import.io to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Import.io works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Import.io to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

985ms average. Fast in production.

Import.io is checked daily against the live service.

Daily averagePeak 1137ms
Oct 3Today
Fastest day
735ms
Slowest day
1137ms
14-day trend
Slowing+9%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Import.io, so you can see the experience inside your AI.

It does not authenticate your account with Import.io. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Import.io Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_cU0m5I8DrW8gA8godx9QuVLKZh1ElrmFOw6PdY9x/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Import.io capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "importio-web-data-extraction-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_cU0m5I8DrW8gA8godx9QuVLKZh1ElrmFOw6PdY9x/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Import.io in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Import.io owners hand off.

This MCP is built for professionals who need to turn the web into a structured database without writing code.

  • 01

    Data Analysts

    They ask the agent to collect market data and pricing intelligence automatically.

  • 02

    Market Researchers

    They use the agent to monitor competitors and perform web audits at scale.

  • 03

    Product Managers

    They hand off crawler health monitoring and data schema verification to their agent.

FAQ

Questions Import.io owners ask.

  • 01

    How do I connect my Import.io account?

    You subscribe to the MCP on Vinkius and enter your Import.io API Key. Once connected, it is ready to use in any compatible client.

  • 02

    Can I extract data from sites without a pre-configured extractor?

    Yes. You can use the run_magic_api capability to automatically identify and pull tabular data from almost any website.

  • 03

    What format will the extracted data be in?

    The agent can retrieve data in structured JSON format or download it as CSV text for use in spreadsheets.

  • 04

    How do I know if my crawl is finished?

    You can ask your agent to check the status of a job. It will report on the current state, success rates, and how many pages have been processed.

  • 05

    Can I monitor my API spending?

    Yes. You can ask your agent to check your account usage to see how many credits you have used and how many remain.

  • 06

    Can I extract data from a website without a pre-configured extractor?

    Yes. Use the run_magic_api capability. It uses Import.io's AI logic to automatically detect and extract structured or tabular data from any URL, making it ideal for quick exploration of new data sources.

  • 07

    How do I monitor the progress of a bulk crawl job?

    Use the get_crawl_status capability by providing the Crawl ID returned when you started the job. Your agent will report the current state, number of pages processed, and success rate in real-time.

  • 08

    Can I get my extracted data in CSV format for spreadsheet analysis?

    Absolutely. Use the download_csv capability with a completed Run ID. Your agent will retrieve the extraction data in CSV format, perfect for processing in capabilities like Excel or Google Sheets.

Explore

More in Developer Tools

Suggestions

Connect Import.io to Claude, Cursor, ChatGPT & more