How to Use the Unstructured MCP in Google ADK

Q: How do I manage Unstructured data workflows with the Google ADK?

You use listprocessingworkflows to choose a pipeline, then triggerworkflowexecution to run it. The MCP Server handles the job ID return, which your agent can track and wait on using BigQuery integration.

Q: What data sources can I list when working with Unstructured in Google ADK?

You use listdatasources to get a definitive list of all remote connectors, such as S3 or GCS. This information feeds directly into your agent's reasoning process on Vertex AI.

Q: Can the Google ADK check job status for Unstructured data?

Yes, by calling listworkflowjobs. Your agent can monitor a running job or look at historical runs to ensure the processed output was successful before proceeding with its core task.

Q: Where does Unstructured process data get listed when using Google ADK?

You use listdatadestinations to see all configured targets, including Vector DBs and SQL. This confirms where the processed results will ultimately land in your Google Cloud environment.

Q: How do I get configuration details for Unstructured with the Google ADK?

Call getworkflowdetails. It pulls up the specific settings and parameters for any given workflow, letting your agent understand exactly how that pipeline is supposed to function.

Connect Unstructured data pipelines into your enterprise workflows using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unstructured MCP to Google ADK

Create your Vinkius account to connect Unstructured 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 Unstructured with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Running Workflows with the MCP Server

Need to run a document processing pipeline right now? The `trigger_workflow_execution` tool manually starts an immediate job. Your agent uses this via Google ADK, getting back a job ID it can monitor for completion. It’s direct action. Instead of waiting for a scheduled batch, your workflow runs on demand the moment your Gemini-powered agent needs to transform data.

Listing Data Sources in Google ADK

The `list_data_sources` tool lets your agent see every connected remote connector. Whether that's S3 or GCS, it lists them out for you. This is crucial when setting up enterprise data ingestion into BigQuery. It gives the Gemini model visibility into all potential inputs before any long-context reasoning starts.

Viewing Workflow Pipelines with MCP Server

To see what’s possible, use `list_processing_workflows`. This lists every end-to-end pipeline configured on the system. Your agent can then select the right process to handle a new dataset. It helps your Google Cloud agents quickly understand the architecture of available Unstructured processing paths.

Setup guide

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

You use `list_processing_workflows` to choose a pipeline, then `trigger_workflow_execution` to run it. The MCP Server handles the job ID return, which your agent can track and wait on using BigQuery integration.

You use `list_data_sources` to get a definitive list of all remote connectors, such as S3 or GCS. This information feeds directly into your agent's reasoning process on Vertex AI.

Yes, by calling `list_workflow_jobs`. Your agent can monitor a running job or look at historical runs to ensure the processed output was successful before proceeding with its core task.

You use `list_data_destinations` to see all configured targets, including Vector DBs and SQL. This confirms where the processed results will ultimately land in your Google Cloud environment.

Call `get_workflow_details`. It pulls up the specific settings and parameters for any given workflow, letting your agent understand exactly how that pipeline is supposed to function.

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