How to Use the Web Scraper MCP in LlamaIndex

Q: How does Web Scraper help with semantic search when using LlamaIndex?

The output from tools like read or extract becomes raw data that LlamaIndex indexes into a vector store. When you query, the system finds similar concepts based on meaning, not just keyword matching.

Q: Can I crawl documentation sites with Web Scraper and LlamaIndex?

Yes, use the crawl tool to explore a site starting from a URL. The resulting document chunks are automatically added to your knowledge base, allowing you to query across multiple pages.

Q: Is Web Scraper good for batch processing when using LlamaIndex?

It's efficient. The batchread tool fetches up to 10 URLs in parallel. This ensures that large batches of articles or documents get processed and indexed quickly, improving the overall performance of your knowledge index.

Q: What if I need specific links from a site using Web Scraper and LlamaIndex?

The listlinks tool extracts all internal hyperlinks. You can then use these link texts or URLs as context when building your RAG application, ensuring the index covers related topics.

Web Scraper | Index live data for semantic search with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Web Scraper to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Structured Metadata

The `extract` tool pulls key metadata—title, description, OG tags, etc.—from a web page. When you run this via your LlamaIndex agent, that structured data becomes part of your searchable knowledge base. You can query past sessions grounded in facts, not just general knowledge. Instead of having to read full pages every time, LlamaIndex indexes these concise metadata points. This makes retrieval faster and keeps the index smaller while retaining high precision.

Building RAG with Clean Content

Use the `read` tool to get clean Markdown from articles or docs. Passing this output to LlamaIndex means that highly readable, structured text gets chunked and indexed for semantic search. This is how you combine live API data with your existing document library. Your RAG application gains immediate power because it can answer questions based on the *actual* content of a webpage, which is then stored in your unified index.

Controlled Site Crawling

The `crawl` tool lets you explore a website starting from one URL, keeping results manageable by limiting it to 10 pages. This process gives the resulting links and content chunks directly into your LlamaIndex index. Developers can build knowledge graphs where live, external site data is incorporated alongside internal documents, letting users query across both sources seamlessly.

Setup guide

Set up Web Scraper MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Web Scraper MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Web Scraper tools.",
)
response = await agent.run("List recent Web Scraper data")

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 LlamaIndex

The output from tools like `read` or `extract` becomes raw data that LlamaIndex indexes into a vector store. When you query, the system finds similar concepts based on meaning, not just keyword matching.

Yes, use the `crawl` tool to explore a site starting from a URL. The resulting document chunks are automatically added to your knowledge base, allowing you to query across multiple pages.

The server touches public web page content and metadata (like titles or descriptions). Specifically, it indexes textual data derived from the main article body, which is Markdown format. No personal identifiers are handled.

It's efficient. The `batch_read` tool fetches up to 10 URLs in parallel. This ensures that large batches of articles or documents get processed and indexed quickly, improving the overall performance of your knowledge index.

The `list_links` tool extracts all internal hyperlinks. You can then use these link texts or URLs as context when building your RAG application, ensuring the index covers related topics.

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