How to Use the Collect MCP in Google ADK

Q: How does Gemini's long context help with large campaigns?

Gemini can ingest every message retrieved by listmessages and every request from listrequests at once. This lets your agent run complex reasoning over your entire communication history to find out why certain cohorts fail to finish their forms.

Connect the Collect MCP Server to Google ADK to analyze massive data collection campaigns with Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Collect MCP to Google ADK

Create your Vinkius account to connect Collect 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 Collect with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run long-context campaign audits with Gemini and Google ADK

Feed your entire campaign history directly into Gemini's million-token context window. By calling `list_campaigns` and pulling every request detail with `get_request`, your agent can spot bottlenecks across thousands of active clients without losing track of the conversation. You can combine this data with your historical tables in BigQuery. The agent checks current submissions, compares them to past quarters, and draft updates based on live user profiles from `get_user_info`.

Automate client follow-ups using Google ADK tools

Stop chasing clients manually for missing documents. Your Google ADK agent can check active requests using `list_requests` via the MCP standard and immediately flag missing elements via `get_element_details` to see exactly what is holding up the process. Once the agent identifies the blocker, it uses `send_message` to ping the contact. Because this runs natively within Vertex AI, you can easily ground the outgoing message text using your corporate guidelines.

Sync external submission data with BigQuery pipelines

Keep your data warehouse up to date without writing complex ETL code. Your agent runs `get_campaign` to pull the latest form structures and pushes those schemas directly into your Google Cloud storage buckets. When users submit their files, the agent monitors the progress using `list_messages`. This keeps your operations team informed of incoming data without anyone having to click around a dashboard.

Setup guide

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

You use the McpToolset class with our streamable HTTP server parameters. Pass the toolset directly into your LlmAgent constructor so your Gemini models can call tools like `create_request` out of the box.

Yes. You can pass a list of tool names to the toolset parameters if you want to restrict your Gemini agent to read-only functions like `get_campaign` and block it from using `send_message`.

It does. While Vinkius hosts the MCP Server as a high-performance HTTP endpoint, the ADK supports both transports, making it easy to test your data collection flows locally before deploying to Vertex AI.

Gemini can ingest every message retrieved by `list_messages` and every request from `list_requests` at once. This lets your agent run complex reasoning over your entire communication history to find out why certain cohorts fail to finish their forms.

All traffic between Google Cloud and our platform is encrypted in transit. Your message lists and campaign structures are processed in ephemeral V8 isolates that wipe all memory as soon as the agent's tool call completes.

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