How to Use the Extracta MCP in Google ADK

Q: How do I load extracted document data into BigQuery using Extracta and Google ADK?

Use uploadfileurl to send the document, poll getresults to get the structured JSON, and then use your Google ADK agent's native BigQuery tool to insert the records.

Q: Can Google ADK automate document classification with Extracta?

Yes, your agent can call createclassification to define document types like invoices or contracts, then check getclassificationresults to route files to specific storage buckets.

Q: How do I configure the Extracta MCP Server inside Google ADK?

Instantiate the McpToolset with the Vinkius HTTP URL and pass it to your LlmAgent. The Gemini model will automatically discover tools like createextraction to parse your files.

Q: How do I modify existing extraction fields?

Call updateextraction to change the schema fields. Your agent can verify the current setup by calling viewextraction before making updates.

Feed structured document data directly into your BigQuery tables using Google ADK and Extracta.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Extracta MCP to Google ADK

Create your Vinkius account to connect Extracta 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 Extracta with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipeline raw documents straight to Google ADK agents

`upload_file_url` is the starting point for your Gemini-powered pipelines to ingest PDFs or images. The tool returns a unique ID that your agent monitors. Your agent uses `get_results` to poll for the completed extraction data. Once the JSON lands, the Google ADK agent can write it directly to BigQuery using native cloud connectors.

Route enterprise files using Gemini and Extracta MCP Server

`create_classification` sets up the routing rules for high-volume document pipelines. This MCP configuration defines the categories like tax forms or bank statements that your Gemini model needs to sort. The agent calls `get_classification_results` to determine the document type. This classification step happens before the agent runs heavy extraction queries, keeping your Google Cloud costs low.

Bulk audit document history in Google Cloud

`get_batch_results` allows your agent to pull historical extraction data in bulk for auditing. This is useful when you need to sync local records with what was processed. The agent can cross-reference these batch results using `view_extraction` to verify which schemas were active during the initial processing run.

Setup guide

Set up Extracta 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 Extracta 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="Extracta_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Extracta 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 Extracta. 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 Extracta 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 Extracta MCP in Google ADK

Use `upload_file_url` to send the document, poll `get_results` to get the structured JSON, and then use your Google ADK agent's native BigQuery tool to insert the records.

Yes, your agent can call `create_classification` to define document types like invoices or contracts, then check `get_classification_results` to route files to specific storage buckets.

Instantiate the `McpToolset` with the Vinkius HTTP URL and pass it to your `LlmAgent`. The Gemini model will automatically discover tools like `create_extraction` to parse your files.

Call `update_extraction` to change the schema fields. Your agent can verify the current setup by calling `view_extraction` before making updates.

Extracta accesses the document URLs you pass to extract raw text and metadata. The Vinkius MCP gateway runs in an ephemeral sandbox, securing your credentials and ensuring document data is never cached or used for model training.

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