Can my agent create a meeting poll with specific date and time options?

Yes. Use the 'create_poll' tool. You can provide a JSON array of option strings (e.g., ['2026-04-01 10:00', '2026-04-02 14:00']). The agent will command the Doodle backend to generate the standard poll structure instantly.

How do I add a participant's vote programmatically via chat?

Use the 'add_participant' tool. Provide the poll ID, the participant's name, and a JSON array of preference values (0=no, 1=yes, 2=if-need-be) matching the number of poll options. The agent will trigger the response routing instantly.

Can I close a poll and set the final meeting time through the agent?

Absolutely. Use the 'close_poll' tool. Provide the poll ID and the text of the winning option. The agent will change the poll state to CLOSED, locking the participation arrays and officially confirming the chosen time.

Doodle MCP Server for Google ADK 10 tools — connect in under 2 minutes

Name: Doodle
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Doodle as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="doodle_agent",
    instruction=(
        "You help users interact with Doodle "
        "using 10 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Doodle MCP Server

Connect your Doodle account to any AI agent and take full control of your group scheduling and meeting polls through natural conversation.

Google ADK natively supports Doodle as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 10 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Poll Orchestration — List all Doodle polls and retrieve explicitly attached array vectors representing titles, states (OPEN/CLOSED), and final chosen options
Live Poll Creation — Provision new group scheduling polls by commanding absolute explicit text payloads for specific dates and times
Participant Auditing — Enumerate explicitly attached user responses active within any target poll to identify precisely who has voted
Programmatic Voting — Trigger absolute response routing to add or remove participant votes, mapping literal preference arrays (Yes, No, If-need-be) exactly
Collaboration Oversight — Retrieve and append string chats and contextual comments attached to specific poll IDs to verify participant feedback
State Management — Change poll states to CLOSED to lock participation arrays and override core settings to dictate finally which exact option won
Data Invalidation — Irreversibly vaporize explicit poll entities and wipe all associated votes and comments from the system permanently

The Doodle MCP Server exposes 10 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Doodle to Google ADK via MCP

Follow these steps to integrate the Doodle MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 10 tools from Doodle via MCP

Why Use Google ADK with the Doodle MCP Server

Google ADK provides unique advantages when paired with Doodle through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Doodle

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Doodle tools with BigQuery, Vertex AI, and Cloud Functions

Doodle + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Doodle MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Doodle and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Doodle tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Doodle regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Doodle

Doodle MCP Tools for Google ADK (10)

These 10 tools become available when you connect Doodle to Google ADK via MCP:

add_comment

Add a comment to a Doodle poll

add_participant

Provide a name and preference array (0=no, 1=yes, 2=if-need-be) matching option quantities. Add a participant vote to a Doodle poll programmatically

close_poll

Overrides the core settings dictating finally which exact option value string won. Close a Doodle poll and set the final chosen option

create_poll

Participants will be invited to vote on their preferred options. Create a new Doodle poll for group scheduling

delete_poll

Drops the raw data out of the system returning completely blank state. Permanently delete a Doodle poll and all associated participant votes and comments

get_comments

Retrieve all comments on a Doodle poll

get_poll

Retrieve detailed information for a specific Doodle poll by ID

list_participants

List all participants who voted on a Doodle poll

list_polls

Returns poll titles, states (OPEN/CLOSED), creation dates, number of participants, and chosen final options. List all Doodle polls created by the authenticated user

remove_participant

The core system inherently recalculates the total votes autonomously. Remove a participant and their votes from a Doodle poll

Example Prompts for Doodle in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Doodle immediately.

"List my Doodle polls"

"Create a poll 'Launch Sync' with options: 'Monday 10am', 'Tuesday 2pm'"

"Who has voted on the 'Team Offsite' poll?"

Troubleshooting Doodle MCP Server with Google ADK

Common issues when connecting Doodle to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Doodle + Google ADK FAQ

Common questions about integrating Doodle MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.