# Import.io MCP for AI Agents AI Agent Connect

> Import.io (Web Data Extraction) MCP lets you pull structured data from any website using your existing Import.io account. You can trigger specific extractors, manage high-volume bulk crawls, and use the Magic API to grab data from pages without any setup. It also tracks your API credits and handles CSV exports for your spreadsheets.

## Overview
- **Category:** developer-tools
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_cU0m5I8DrW8gA8godx9QuVLKZh1ElrmFOw6PdY9x/ai-agent-connect
- **Tags:** data-extraction, web-crawling, structured-data, json-export, automation, data-pipeline

## Description

Import.io (Web Data Extraction) MCP puts the power of professional-grade web scraping directly into your AI agent's hands. Instead of writing custom Python scripts or wrestling with headless browsers, you can just tell your agent to go grab the latest pricing from a competitor or pull a list of products from a retail site. It connects to your existing Import.io account so you can use the extractors you've already built or fire off new ones on the fly. If you're dealing with messy, unstructured pages, the Magic API handles the heavy lifting of identifying tables and lists automatically. You can also manage large-scale projects by starting bulk crawls and checking their progress while you move on to other tasks. It's a way to turn the open web into a structured database for your specific needs without the usual technical friction. Finding this in the Vinkius catalog makes it easy to plug into your existing workflow and start moving data from a browser into your actual work.

## Tools

### get_crawl_data
Pull the combined JSON output from a finished crawl job. This is useful for moving data into a database.

### get_crawl_status
See how many pages a bulk crawl has finished and its current success rate. Use this to monitor long jobs.

### account_usage
View your remaining monthly API credits and subscription limits. This helps you stay on top of your budget.

### download_csv
Get a CSV version of your extracted data for use in spreadsheets. It skips the manual conversion step.

### get_extractor_data
Grab the JSON results from a specific, completed extraction run. This gives you the raw data for your agent.

### list_extractors
See every extractor currently configured in your Import.io account. This helps you find the right tool ID.

### run_magic_api
Let the automated Magic API find and pull data from an unstructured URL. It is perfect for quick exploration.

### run_extractor
Start a specific extraction for a URL and get a run ID to track it. This is for targeted data pulls.

### start_crawl
Kick off a large-scale crawl across many pages at once. This handles high-volume data collection jobs.

### get_extractor_status
Check if your specific extraction is still running, finished, or failed. Use this to poll for results.

## Prompt Examples

**Prompt:** 
```
Can you get the current prices for the top 10 laptops on https://example.com/laptops?
```

**Response:** 
```
I've started pulling the data from that page. Here are the top 10 laptops currently listed:

| Model | Price | Rating |
| :--- | :--- | :--- |
| **ProBook X** | $1,299 | 4.8 |
| **Zenith 15** | $1,150 | 4.5 |
| **UltraTab** | $999 | 4.2 |

*Note: Prices are in USD. I've extracted the structured data directly from the site.*
```

**Prompt:** 
```
List my extractors and tell me which one is for Amazon.
```

**Response:** 
```
I've found the following extractors in your account:
- **Amazon Scraper** (ext-001)
- **Competitor Pricing** (ext-002)
- **Real Estate Leads** (ext-003)

The **Amazon Scraper** (ext-001) is the one you're looking for. Would you like me to run it for a specific URL?
```

**Prompt:** 
```
How many credits do I have left this month?
```

**Response:** 
```
You have **37,550 credits** remaining for this billing cycle. 

- **Used:** 12,450 credits
- **Limit:** 50,000 credits

Your account health is excellent, and you have plenty of room for more extractions this month.
```

## Capabilities

### Trigger specific extractors
Run predefined scrapers on specific URLs to get clean JSON data back immediately.

### Start bulk crawls
Kick off large-scale data collection jobs across thousands of pages concurrently.

### Extract tabular data automatically
Use the Magic API to identify and pull tables from websites without any manual rules.

### Monitor crawl progress
Check the real-time status of ongoing jobs to see success rates and page counts.

### Download CSV results
Get your extracted data in a format ready for immediate use in spreadsheets.

### Audit API credit usage
Check your remaining monthly credits to manage your data extraction budget.

## Use Cases

### Competitor Pricing Analysis
A researcher asks for a table of prices from a rival site. The agent uses run_magic_api to grab the data and present it as a clean table.

### Bulk Inventory Collection
A manager needs 5,000 product links. The agent uses start_crawl to begin the job and get_crawl_status to monitor the progress.

### Schema Validation
A developer wants to see what an extractor returns for a specific site. The agent uses list_extractors and run_extractor to test it.

### Budget Tracking
An analyst wants to know if they have enough credits for a big job today. The agent uses account_usage to check the remaining balance.

## Benefits

- Skip the manual copy-pasting of product lists by using run_extractor to get clean JSON instantly.
- Manage high-volume data collection projects with start_crawl to handle thousands of pages at once.
- Get data into your spreadsheets faster using download_csv to skip the JSON to CSV conversion step.
- Handle unpredictable websites easily with run_magic_api to identify tables without manual rules.
- Stay on top of your costs by checking your remaining credits with account_usage before starting big jobs.
- Save time on setup by using list_extractors to find the right tool for the job in your account.

## How It Works

The bottom line is you get production-ready web data in your chat window without touching a line of scraping code.

1. Connect your Import.io API key to the Connector.
2. Tell your agent which URL or extractor to use.
3. Get back structured JSON or CSV data.

## Frequently Asked Questions

**Does Import.io (Web Data Extraction) work on sites with lots of Javascript?**
Yes, it uses Import.io's infrastructure to handle dynamic content and JS rendering, making it much more reliable than simple scraping scripts.

**Can I use Import.io (Web Data Extraction) to get data into Excel?**
Yes, you can download your extracted data as a CSV file, which opens directly in Excel or Google Sheets for easy analysis.

**How do I handle sites that block scrapers with Import.io (Web Data Extraction)?**
The Connector uses a managed proxy network to bypass most common blocks and CAPTCHAs, ensuring your data collection stays on track.

**Can I run a crawl on 1,000 pages at once with Import.io (Web Data Extraction)?**
Yes, the bulk crawl tool is specifically designed for large-scale data collection across many pages concurrently.

**Is there a way to see my credit balance with Import.io (Web Data Extraction)?**
Yes, you can simply ask your agent to check your account usage at any time to see your remaining monthly credits.

**Does Import.io (Web Data Extraction) require me to write any code?**
No, you just describe the task to your agent in plain English and it uses the Connector to handle the technical work of getting the data.

**Can I extract data from a website without a pre-configured extractor?**
Yes. Use the `run_magic_api` tool. 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.

**How do I monitor the progress of a bulk crawl job?**
Use the `get_crawl_status` tool 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.

**Can I get my extracted data in CSV format for spreadsheet analysis?**
Absolutely. Use the `download_csv` tool with a completed Run ID. Your agent will retrieve the extraction data in CSV format, perfect for processing in tools like Excel or Google Sheets.