How to Use the Import.io (Web Data Extraction) MCP in Pydantic AI

Q: How does Pydantic AI validate data from Import.io (Web Data Extraction)?

The agent calls getextractordata on the MCP Server and parses the JSON output through a Pydantic model. Any schema mismatch triggers a validation error immediately.

Q: Can I run an ad-hoc scrape using Import.io (Web Data Extraction) in Pydantic AI?

Yes, your agent can call runmagicapi with a target URL. The resulting JSON is structured on the fly and validated.

Q: How does the agent track long-running crawls?

The agent triggers startcrawl and polls getcrawlstatus using its run loop. Once completed, it fetches the data via getcrawldata.

Q: Is the MCP Server compatible with the latest Pydantic AI toolset format?

Yes, you connect using the unified MCPToolset class pointing to the HTTP endpoint. This exposes all ten tools to your agent.

Run type-safe web scrapers that validate extracted data against Pydantic models at runtime using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Import.io (Web Data Extraction) MCP to Pydantic AI

Create your Vinkius account to connect Import.io (Web Data Extraction) to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Import.io (Web Data Extraction) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Web Extraction with Pydantic AI

Your agent executes `get_extractor_data` to fetch structured JSON payloads from completed extraction runs. This tool delivers clean web data that Pydantic AI validates against your defined schemas using this MCP Server. If the target website changes its structure and returns unexpected fields, the validation layer catches it instantly. Catching these anomalies early prevents corrupted data from entering your production database.

Programmatic Crawl Control and Validation

The MCP Server uses `start_crawl` to spin up parallel web extraction jobs across entire domains. Managing these large-scale runs programmatically means you never have to write custom scrapers. Checking progress is straightforward via `get_crawl_status`, and the agent downloads the final dataset using `get_crawl_data`. Every returned JSON payload must match your Pydantic model before the agent continues execution.

Ad-Hoc Scraping and Usage Audits

Your agent calls `run_magic_api` to scrape dynamic websites on the fly without setting up an extractor beforehand. This tool handles JavaScript rendering and anti-bot bypasses automatically. To keep costs in check, the agent queries `account_usage` before starting heavy tasks. It can also use `download_csv` to grab raw tabular data for quick processing.

Setup guide

Set up Import.io (Web Data Extraction) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "importio-web-data-extraction-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Import.io (Web Data Extraction) tools.",
)

result = await agent.run("List recent Import.io (Web Data Extraction) transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Import.io. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Import.io (Web Data Extraction) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Import.io (Web Data Extraction) MCP in Pydantic AI

The agent calls `get_extractor_data` on the MCP Server and parses the JSON output through a Pydantic model. Any schema mismatch triggers a validation error immediately.

Yes, your agent can call `run_magic_api` with a target URL. The resulting JSON is structured on the fly and validated.

The agent triggers `start_crawl` and polls `get_crawl_status` using its run loop. Once completed, it fetches the data via `get_crawl_data`.

Yes, you connect using the unified `MCPToolset` class pointing to the HTTP endpoint. This exposes all ten tools to your agent.

Your API credentials and extracted JSON schemas are processed in isolated, single-use V8 environments. How this MCP Server protects your data is simple: no data is stored or logged on Vinkius servers.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript