How to Use the Urlbox MCP in LlamaIndex

Q: Can I filter index results based on URL properties using Urlbox and LlamaIndex?

Because getmetadata captures structured attributes, you can use those fields to build precise filters. You're not just searching text; you're querying the structure of the web data itself.

Index Web Data and Visual Content 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 Urlbox MCP to LlamaIndex

Create your Vinkius account to connect Urlbox 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 Urlbox with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Building Searchable Indexes with MCP Server

LlamaIndex turns live web data into a persistent knowledge base. You can use the `generate_pdf` tool on an external URL, and then index that resulting document chunk. This means your RAG application can search the PDF's contents later, even if you never query it again. This capability allows you to combine documents created by various MCP Server tools into one unified, searchable vector store for semantic queries.

Deep Visual Data Retrieval with LlamaIndex

The `take_full_page_screenshot` tool output can be indexed and queried. Instead of just asking if a page is 'broken,' you ask your index, 'What visual elements were present on the homepage last week?' The answer comes grounded in the stored screenshot data. This transforms simple web scraping into deep knowledge retrieval, letting users query past visual configurations or website states.

Metadata-Driven Querying for LlamaIndex

Use `get_metadata` to capture key details about a URL—like publication date or author. Indexing this metadata allows you to filter your knowledge base by specific attributes, not just keywords. You can ask the index, 'Show me all URLs from Q2 that were published on an image-heavy page.' This structured approach makes your RAG applications far more precise than simple text searches.

Setup guide

Set up Urlbox 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 Urlbox 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 Urlbox tools.",
)
response = await agent.run("List recent Urlbox 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 Urlbox. 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 Urlbox 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 Urlbox MCP in LlamaIndex

You pass the output of an MCP Server tool (like a PDF file generated by `generate_pdf`) to LlamaIndex. The index then breaks down that content, creating searchable vector embeddings.

Yes. By repeatedly running screenshot tools and indexing the results, you build a timeline of visual changes. Your index lets you retrieve answers grounded in specific past screenshots or metadata sets.

The server touches URL content and metadata. This includes text from PDFs, raw visual image data from screenshot methods, and structured key/value pairs gathered by `get_metadata`.

You wrap the MCP Server tools into a FunctionAgent. LlamaIndex handles the conversion so you can easily pass those functions to your retrieval pipeline, letting them feed data directly into the vector store.

Because `get_metadata` captures structured attributes, you can use those fields to build precise filters. You're not just searching text; you're querying the structure of the web data itself.

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