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

Q: Can I run semantic search queries over bulk crawls managed by Import.io (Web Data Extraction) in LlamaIndex?

Yes, the agent can call startcrawl and wait for completion via getcrawlstatus. Once done, it pulls the data using getcrawldata and indexes the entire batch into your vector store.

Q: How do I prevent indexing empty or failed crawls from Import.io (Web Data Extraction) in my LlamaIndex pipeline?

The agent checks the status using getextractorstatus before attempting to pull data. If the status is failed, the agent skips the indexing step to keep your vector store clean.

Q: Can I query my current API usage directly from a LlamaIndex chat interface?

Yes, the accountusage tool allows your agent to check and report your remaining API credits in real time. This keeps you informed of your running costs during heavy indexing jobs.

Build searchable knowledge bases from live web extractions using LlamaIndex and the Import.io (Web Data Extraction) MCP Server.

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 LlamaIndex

Create your Vinkius account to connect Import.io (Web Data Extraction) 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 Import.io (Web Data Extraction) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live web extractions directly into LlamaIndex

The `get_extractor_data` tool fetches structured JSON payloads from finished extraction runs to feed your vector index. LlamaIndex parses this structured data, turning raw web fields into searchable node documents. By calling `list_extractors`, your index query engine knows exactly which data sources are available to query. This eliminates outdated context by pulling live data on demand instead of relying on static files.

Ground your RAG applications in real-time web structures

The `run_magic_api` tool lets your query engine extract clean data from unconfigured websites when a standard extractor does not exist. This raw output is immediately indexed to answer specific user queries. You can track the status of these on-the-fly extractions using `get_extractor_status` to ensure your search index only ingests completed runs. This keeps your vector store free of partial or corrupted data.

Feed bulk web crawls into your vector stores

The `start_crawl` tool initiates concurrent multi-page crawls that generate massive amounts of web data for your knowledge base. LlamaIndex monitors the crawl state using `get_crawl_status` before processing the final output. Once completed, `get_crawl_data` retrieves the unified JSON payload, which the McpToolSpec converts into document nodes. This MCP server integration ensures your knowledge base stays updated with fresh web data.

Setup guide

Set up Import.io (Web Data Extraction) 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 Import.io (Web Data Extraction) 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 Import.io (Web Data Extraction) tools.",
)
response = await agent.run("List recent Import.io (Web Data Extraction) 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 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 LlamaIndex

You register the server with McpToolSpec and pass the tools to a FunctionAgent. The agent calls `get_extractor_data` and converts the structured JSON response into document nodes for your vector store.

Yes, the agent can call `start_crawl` and wait for completion via `get_crawl_status`. Once done, it pulls the data using `get_crawl_data` and indexes the entire batch into your vector store.

The agent checks the status using `get_extractor_status` before attempting to pull data. If the status is failed, the agent skips the indexing step to keep your vector store clean.

Yes, the `account_usage` tool allows your agent to check and report your remaining API credits in real time. This keeps you informed of your running costs during heavy indexing jobs.

Data processed by the MCP server is held in ephemeral memory inside the Vinkius secure sandbox. It is immediately transferred to your local LlamaIndex vector store, leaving no persistent footprint on our 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