How to Use the Affinda MCP in Google ADK

Q: How do I configure Affinda with Google ADK?

Install the google-adk package. Set up an McpToolset using StreamableHttpServerParameters with your Vinkius URL, then pass it to your LlmAgent.

Q: Can Google ADK filter which Affinda tools the agent sees?

You apply the toolnames parameter when initializing the toolset. You can restrict one agent to createdocument while limiting another to just listdocuments.

Q: How does the Affinda MCP Server handle large document batches in Google ADK?

The agent uses listdocuments to pull status updates across your workspace. Once ready, Gemini reads the extracted JSON and can hold massive amounts of that structured data in its 1M+ token context window.

Q: Does this integration support BigQuery workflows?

Agents can take the JSON output from getdocument and write it directly to your data warehouse. The ADK handles the connection between the MCP tool and your Google Cloud infrastructure.

Feed structured document data from Affinda directly into Google ADK agents for deep reasoning with long-context Gemini models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Affinda MCP to Google ADK

Create your Vinkius account to connect Affinda 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 Affinda with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extract Invoices for Google ADK Agents

The `create_document` tool pushes public PDF URLs into Affinda and returns structured JSON for your Gemini agents to analyze. You get accurate extraction without writing custom parsing logic. Gemini's massive context window excels when you feed it hundreds of extracted fields at once. Your agent pulls the final payload via `get_document` and can immediately cross-reference those details against BigQuery datasets.

Map Affinda Workspaces to Cloud Storage

Your agent reads available container environments using the `list_workspaces` tool. This tells the system exactly where to look for incoming files before routing them through Vertex AI pipelines. Restricting access is simple with the Google ADK. You apply the `tool_names` filter in your `McpToolset` configuration to expose only workspace reading capabilities to specific lower-privileged agents.

Audit Batch Processing via MCP

Running `list_documents` gives your agent a complete view of every parsed file and its current processing status. The agent knows exactly which resumes or passports are ready for review. Calling `list_document_types` confirms which parsing models are active on your account. If the agent needs to process an unfamiliar ID format, it checks this list before throwing an error.

Setup guide

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

Install the `google-adk` package. Set up an `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL, then pass it to your `LlmAgent`.

You apply the `tool_names` parameter when initializing the toolset. You can restrict one agent to `create_document` while limiting another to just `list_documents`.

The agent uses `list_documents` to pull status updates across your workspace. Once ready, Gemini reads the extracted JSON and can hold massive amounts of that structured data in its 1M+ token context window.

Agents can take the JSON output from `get_document` and write it directly to your data warehouse. The ADK handles the connection between the MCP tool and your Google Cloud infrastructure.

Processing happens through a zero-trust architecture. Vinkius routes the public URL and resulting JSON through an isolated sandbox that destroys itself immediately after your agent receives the response.

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