How to Use the Web Scraper MCP in Pydantic AI

Q: Can I use Web Scraper in Pydantic AI to map links?

Yes, the listlinks tool pulls internal hyperlinks. Because of Pydantic validation, you can be sure that the link list returned is correctly formatted and includes only valid relative paths.

Q: What metadata fields does Web Scraper provide when using Pydantic AI?

The extract tool provides title, description, OG tags, language codes, and canonical URLs. Since the response is validated, you can treat these values as guaranteed data types.

Q: What are the limitations when using Web Scraper with Pydantic AI?

The crawl tool limits its exploration to 10 pages maximum. This restriction helps maintain predictable response size and ensures that the resulting dataset remains manageable for your agent's processing context.

Scrape web content and validate data types using Web Scraper with 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 Web Scraper MCP to Pydantic AI

Create your Vinkius account to connect Web Scraper 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 Web Scraper with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Metadata Extraction with MCP Server

Use the `extract` tool to pull structured metadata from a page. The response gives you title, description, OG tags, and more—all validated against Pydantic models. Since every field is typed at runtime, your agent knows exactly what it's getting: if an expected field is missing or wrong, the whole process fails loudly. No silent corruption.

Bulk Fetching for Type-Safe Data

The `batch_read` tool fetches multiple web pages in parallel, handling up to 10 URLs at a time. The Pydantic layer validates the output from every single page. This ensures that even when dealing with dozens of sources, you only receive data structured exactly how your Python code expects it.

Clean Content Retrieval for Pydantic AI

The `read` tool uses Reader View to pull out clean Markdown content from any public page. This output is then validated, ensuring the main article body conforms to your expected schema. It’s crucial when you need the agent to process large amounts of text while maintaining data integrity. You won't get messy HTML chunks.

Setup guide

Set up Web Scraper 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": {
        "web-scraper-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Web Scraper 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 Web Scraper. 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 Web Scraper 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 Web Scraper MCP in Pydantic AI

The server provides typed, structured output for web content. When your agent calls a tool like `extract`, the data is instantly validated against models, preventing runtime errors from bad API responses.

Yes, the `list_links` tool pulls internal hyperlinks. Because of Pydantic validation, you can be sure that the link list returned is correctly formatted and includes only valid relative paths.

The `extract` tool provides title, description, OG tags, language codes, and canonical URLs. Since the response is validated, you can treat these values as guaranteed data types.

The `crawl` tool limits its exploration to 10 pages maximum. This restriction helps maintain predictable response size and ensures that the resulting dataset remains manageable for your agent's processing context.

The server handles structured metadata, including titles, descriptions, OG tags, authors, link counts, and canonical URLs. All these pieces are validated as predictable Python types.

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