How to Use the Doodle MCP in Google ADK

Q: How do I initialize the Doodle MCP Server in Google ADK?

You instantiate McpToolset with the HTTP transport parameters pointing to your Vinkius endpoint. Pass this toolset directly into your LlmAgent tools list, and Gemini will instantly discover tools like createpoll.

Q: Can Gemini write comments on a Doodle poll using Google ADK?

Yes, your agent can call addcomment to write text updates to any active poll. You feed the context from Vertex AI, and the model constructs the payload to post the comment via the server.

Q: How does Google ADK restrict access to the Doodle delete tool?

You can use the toolnames filter in your McpToolset configuration to exclude deletepoll. This ensures your Gemini agent can read and update polls but lacks the authorization to destroy them.

Connect your Google ADK enterprise agents directly to Doodle to schedule client syncs using Gemini's long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Doodle MCP to Google ADK

Create your Vinkius account to connect Doodle 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 Doodle with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Doodle polls inside Google ADK pipelines

This MCP Server provides the `get_poll` tool to feed full Doodle participant vote sheets directly into your Google ADK context window. Gemini parses thousands of tokens of Doodle scheduling data to find the absolute best meeting times across complex team structures. The Google ADK agent uses `list_polls` to pull your complete Doodle scheduling history into Vertex AI. This lets your enterprise agent analyze past Doodle meeting patterns and make smarter decisions before calling `create_poll` for new client syncs.

Programmatic participant and comment management

Use the `add_participant` tool within your Google ADK workflow to sync external calendar responses back to your active Doodle poll. The Google agent maps client preferences directly from emails processed in your Google Cloud pipeline to Doodle. To keep communication centralized, the Google ADK agent calls `add_comment` to post updates or context links directly on the Doodle poll. You can retrieve these Doodle threads anytime using `get_comments` to log the decision history inside BigQuery.

Finalize and clean up enterprise polls

The `close_poll` tool allows your Google ADK agent to lock the chosen Doodle date once Gemini confirms all key stakeholders have voted. This writes the final decision directly to the Doodle poll and prepares the Google Calendar invite payload via the MCP tool. If a project gets shelved, the Google ADK agent calls `delete_poll` to remove the Doodle records. Because Google ADK integrates with your GCP IAM policies, you can restrict this destructive Doodle action to authorized service accounts only.

Setup guide

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

You instantiate `McpToolset` with the HTTP transport parameters pointing to your Vinkius endpoint. Pass this toolset directly into your `LlmAgent` tools list, and Gemini will instantly discover tools like `create_poll`.

Yes, your agent can call `add_comment` to write text updates to any active poll. You feed the context from Vertex AI, and the model constructs the payload to post the comment via the server.

You can use the `tool_names` filter in your `McpToolset` configuration to exclude `delete_poll`. This ensures your Gemini agent can read and update polls but lacks the authorization to destroy them.

You can write a Google ADK script that pulls participant lists from BigQuery and uses `add_participant` to populate your polls. This bridges your enterprise data warehouse directly with your active scheduling workflows.

All participant names, preference arrays, and poll comments are processed in an isolated, secure MCP sandbox. Your scheduling data never trains the underlying Gemini models and is encrypted in transit using standard TLS protocols.

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