How to Use the LlamaCloud (Managed RAG & Parsing) MCP in Google ADK

Q: How does LlamaCloud (Managed RAG & Parsing) integrate with Google ADK agents?

You register the server as an McpToolset inside your Python script. The Google ADK agent auto-discovers the tools and calls them to parse files or query pipelines on demand.

Q: Can Gemini models in Google ADK call LlamaCloud (Managed RAG & Parsing) tools directly?

Yes, Gemini uses native tool-calling to run createparsingupload when a user uploads a PDF. The model handles the asynchronous polling until the text is ready.

Q: How do I limit which tools the Google ADK agent can access?

You use the toolnames filter when initializing the toolset in Python. This restricts the agent to specific operations, like only allowing document parsing and blocking pipeline configuration tools.

Feed structured PDF data into Gemini's long-context window using Google ADK and this 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 LlamaCloud (Managed RAG & Parsing) MCP to Google ADK

Create your Vinkius account to connect LlamaCloud (Managed RAG & Parsing) to Google ADK 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 LlamaCloud (Managed RAG & Parsing) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse enterprise PDFs for Gemini reasoning

The `create_parsing_upload` tool extracts structured markdown from complex documents and feeds it directly to your Google ADK agent. This lets Gemini process massive tables alongside your BigQuery datasets without losing formatting. Your agent calls `get_parsing_result` to retrieve the clean text once the extraction finishes. By bypassing manual OCR, your pipeline feeds high-fidelity text straight into Gemini's million-token context window.

Manage active ingestion pipelines

The `list_pipelines` tool lets your Google ADK agent inspect your active LlamaCloud ingestion setups on Google Cloud. Your agent can dynamically choose the right pipeline based on user input. By calling `get_pipeline`, the agent reads the pipeline's metadata to verify index configurations before running search tasks. This keeps your enterprise data flows transparent and easily auditable.

Track active ingestion jobs programmatically

The `list_parsing_jobs` tool exposes the state of all active document extractions to your running Google ADK agent. Your agent can monitor long-running jobs without polling external dashboards. This MCP Server integration allows your agent to coordinate multi-step data ingestion tasks directly from your terminal. It ensures your Vertex AI models only read fully processed documents.

Setup guide

Set up LlamaCloud (Managed RAG & Parsing) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with LlamaCloud (Managed RAG & Parsing) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="LlamaCloud (Managed RAG & Parsing)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LlamaCloud (Managed RAG & Parsing) tools via MCP.",
    tools=mcp_tools,
)

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 LlamaCloud. 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 LlamaCloud (Managed RAG & Parsing) 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 LlamaCloud (Managed RAG & Parsing) MCP in Google ADK

You register the server as an `McpToolset` inside your Python script. The Google ADK agent auto-discovers the tools and calls them to parse files or query pipelines on demand.

Yes, Gemini uses native tool-calling to run `create_parsing_upload` when a user uploads a PDF. The model handles the asynchronous polling until the text is ready.

Yes, your agent can query BigQuery for structured data and use this server to parse unstructured PDFs simultaneously. This lets you combine relational databases with parsed PDF content in a single run.

You use the `tool_names` filter when initializing the toolset in Python. This restricts the agent to specific operations, like only allowing document parsing and blocking pipeline configuration tools.

All document streams are processed through an isolated, zero-trust V8 sandbox that handles authentication via a single secure token. Your files are transmitted using encrypted HTTPS channels directly to LlamaCloud without persistent storage on Vinkius.

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