How to Use the Browse AI MCP in LlamaIndex

Q: How do I index Browse AI outputs into a LlamaIndex vector store?

Your agent uses gettask to retrieve the scraped JSON payload. It then wraps this text in a LlamaIndex Document and inserts it into your vector index for immediate semantic querying.

Q: Can LlamaIndex select the right Browse AI robot automatically?

Yes. By indexing the output of listrobots, your LlamaIndex agent searches the metadata of your scrapers to match the user's intent with the correct robot ID.

Q: How do I configure the Browse AI MCP tool spec in LlamaIndex?

Install llama-index-tools-mcp and pass the Vinkius endpoint to the client. Convert the client to a tool list and hand them to your LlamaIndex FunctionAgent.

Q: Can I monitor extraction status asynchronously?

Yes. Your agent can poll gettask to check the status of a run. Once the status field marks the run as complete, the agent proceeds to load the extracted data.

Index live Browse AI extraction data into LlamaIndex vector stores for instant RAG search over freshly scraped web pages.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browse AI MCP to LlamaIndex

Create your Vinkius account to connect Browse AI 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 Browse AI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index raw web extractions directly into RAG

The `get_task` tool retrieves structured data from completed Browse AI scraping jobs. Your LlamaIndex agent calls this tool to pull fresh web content and instantly converts the payload into indexable Document objects. This setup eliminates static data lag. Instead of querying outdated vector databases, your agent runs `run_robot` on demand, indexes the fresh output, and answers user queries using the most current web data.

Audit robot configurations for semantic search

The `get_robot` tool exposes the active configuration and extraction schemas of your Browse AI scraping robots. This MCP Server exposes robot configurations so your agent can semantically search for the right scraper based on user queries. When a user asks for retail prices, the agent searches its index of robot definitions. It locates the target robot via `list_robots` and executes it without hardcoded routing.

Search historical extraction monitors

The `list_monitors` tool allows LlamaIndex agents to inspect active tracking schedules on target websites. By adding this MCP Server to your LlamaIndex pipeline, your agent indexes these schedules to understand how frequently specific web sources are updated. By querying this local index, the agent decides whether to pull cached data from `get_bulk_run` or trigger a fresh run. This keeps your vector store updated while keeping API costs low.

Setup guide

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

Your agent uses `get_task` to retrieve the scraped JSON payload. It then wraps this text in a LlamaIndex Document and inserts it into your vector index for immediate semantic querying.

Yes. By indexing the output of `list_robots`, your LlamaIndex agent searches the metadata of your scrapers to match the user's intent with the correct robot ID.

Install `llama-index-tools-mcp` and pass the Vinkius endpoint to the client. Convert the client to a tool list and hand them to your LlamaIndex `FunctionAgent`.

Yes. Your agent can poll `get_task` to check the status of a run. Once the status field marks the run as complete, the agent proceeds to load the extracted data.

Your extracted web data and task histories are processed entirely in-memory within your local LlamaIndex pipeline. Vinkius secures the transport layer with ephemeral, zero-trust tokens, ensuring your scraped payloads are never exposed.

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