Can it read documentation sites that are split into multiple pages?

Yes! You can use the `crawl` tool. For example: 'Crawl the getting started guide at https://example.com/docs'. The agent will fetch the starting page and automatically follow inner links to gather up to 10 pages of context.

How does it handle ads and cluttered websites?

The `read` tool uses the same underlying technology as Firefox's 'Reader View' (@mozilla/readability). It intelligently strips out standard website boilerplate—like navbars, sidebars, footers, and ads—leaving only the title and the clean main article text converted to Markdown.

Is there a limit on how many URLs I can batch process?

Yes, to ensure conversational AI latency remains reasonable, the `batch_read` tool accepts a maximum of 10 URLs in a single request. All 10 URLs are fetched simultaneously in parallel for maximum speed.

Web Scraper MCP Server for OpenAI Agents SDK 5 tools — connect in under 2 minutes

Name: Web Scraper
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 5 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Web Scraper through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Web Scraper Assistant",
            instructions=(
                "You help users interact with Web Scraper. "
                "You have access to 5 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Web Scraper"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Web Scraper MCP Server

Connect the Web Scraper utility to any AI agent to give it direct access to the public internet. Instead of letting the AI hallucinate facts, allow it to read real-time articles, parse documentation, and fetch clean text from any URL you provide.

The OpenAI Agents SDK auto-discovers all 5 tools from Web Scraper through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Web Scraper, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Reader View — Convert any cluttered webpage into pristine, readable Markdown by stripping out ads, navbars, and boilerplate using Mozilla Readability logic
Site Crawling — Instruct the AI to crawl a starting URL (like a documentation hub or wiki) up to 10 pages deep automatically
Batch Processing — Fetch up to 10 different URLs in parallel to compare articles or summarize multiple sources at once
Metadata Extraction — Quickly pull SEO titles, descriptions, OG tags, canonical links, and all outbound hyperlinks without downloading the entire page body

The Web Scraper MCP Server exposes 5 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Web Scraper to OpenAI Agents SDK via MCP

Follow these steps to integrate the Web Scraper MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 5 tools from Web Scraper

Why Use OpenAI Agents SDK with the Web Scraper MCP Server

OpenAI Agents SDK provides unique advantages when paired with Web Scraper through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Web Scraper + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Web Scraper MCP Server delivers measurable value.

Automated workflows: build agents that query Web Scraper, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Web Scraper, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Web Scraper tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Web Scraper to resolve tickets, look up records, and update statuses without human intervention

Web Scraper MCP Tools for OpenAI Agents SDK (5)

These 5 tools become available when you connect Web Scraper to OpenAI Agents SDK via MCP:

batch_read

All URLs are fetched in parallel. Maximum 10 URLs per batch. Fetch multiple web pages in parallel

crawl

Maximum 10 pages to keep response size manageable. Crawl a website starting from a URL

extract

Returns: title, description, OG tags, lang, author, robots, canonical, link count. For the full page content, use the read tool instead. Extract structured metadata from a web page: title, description, OG tags, and more

list_links

Internal links share the same hostname as the source page. Extract all hyperlinks from a web page

read

Uses @mozilla/readability (Firefox Reader View) to extract the main article content, then converts to Markdown. Works best for articles, docs, blogs, and Wikipedia. Fetch any public web page and return its full content as clean Markdown

Example Prompts for Web Scraper in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Web Scraper immediately.

"Read https://en.wikipedia.org/wiki/Artificial_intelligence and summarize its history."

"Extract the links from https://news.ycombinator.com/"

"Compare these two links: url1.com and url2.com"

Troubleshooting Web Scraper MCP Server with OpenAI Agents SDK

Common issues when connecting Web Scraper to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Web Scraper + OpenAI Agents SDK FAQ

Common questions about integrating Web Scraper MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.