How to Use the Doodle MCP in OpenAI Agents SDK

Q: How do I pass Doodle credentials to my OpenAI Agents SDK pipeline?

You pass your Vinkius endpoint token into the MCPServerStreamableHttpParams when initializing the stream. The SDK handles the header propagation, meaning your agent accesses createpoll and other tools without exposing raw API keys in the agent code.

Q: Can an OpenAI Agents SDK agent close a Doodle poll autonomously?

Yes, your agent can evaluate the results returned by getpoll and call closepoll to finalize the meeting. We recommend setting up a guardrail step in your SDK pipeline to confirm the selected time slot doesn't conflict with your primary calendar.

Q: How does the OpenAI Agents SDK handle Doodle voting errors?

If addparticipant fails due to an invalid preference array, the SDK captures the trace on your OpenAI dashboard. The agent reads the error block and can retry the request with corrected parameters automatically.

Get your OpenAI Agents SDK pipelines scheduling meetings directly through Doodle without writing custom API polling logic.

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 OpenAI Agents SDK

Create your Vinkius account to connect Doodle to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate poll creation in OpenAI Agents SDK pipelines

This MCP Server exposes the `create_poll` tool so your OpenAI Agents SDK system can spin up new Doodle polls directly from conversation threads. Your agent handles the initial setup, gets the Doodle poll ID, and passes it to the next agent in your safety-guarded OpenAI pipeline. By calling `list_polls`, your OpenAI system checks your active Doodle scheduling requests before generating duplicates. This keeps your OpenAI dashboard traces clean because the agent only triggers a poll when it verifies no matching Doodle event exists.

Real-time Doodle participant tracking and voting

Use the `add_participant` tool inside your OpenAI Agents SDK setup to programmatically record Doodle voting preferences based on incoming Slack messages. The agent parses the raw text, maps the choices to the Doodle preference array, and updates the poll without human intervention. If someone changes their mind, the OpenAI agent runs `remove_participant` to recalculate the Doodle standings. Because the OpenAI Agents SDK supports strict runtime validation, you won't worry about corrupted voting arrays breaking the Doodle schema.

Finalize Doodle meetings with guardrail validation

The `close_poll` tool lets your agent lock in the winning Doodle slot using this MCP integration. In your OpenAI Agents SDK setup, you can configure a supervisor agent to inspect the Doodle poll data via `get_poll` before committing the final decision. For cancelled syncs, the OpenAI agent executes `delete_poll` to clear the Doodle records from your dashboard. This structure prevents accidental Doodle deletions by forcing the OpenAI agent to run a pre-check verification step before dropping the raw data.

Setup guide

Set up Doodle MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Doodle tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Doodle tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Doodle tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Doodle Agent",
            instructions="You have access to Doodle tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You pass your Vinkius endpoint token into the `MCPServerStreamableHttpParams` when initializing the stream. The SDK handles the header propagation, meaning your agent accesses `create_poll` and other tools without exposing raw API keys in the agent code.

Yes, your agent can evaluate the results returned by `get_poll` and call `close_poll` to finalize the meeting. We recommend setting up a guardrail step in your SDK pipeline to confirm the selected time slot doesn't conflict with your primary calendar.

If `add_participant` fails due to an invalid preference array, the SDK captures the trace on your OpenAI dashboard. The agent reads the error block and can retry the request with corrected parameters automatically.

You control tool exposure by defining specific agent schemas in your Python code. If you only want an agent to read data, expose `get_poll` and `list_participants` while omitting destructive tools like `delete_poll`.

Your poll titles, participant votes, and comments pass through a zero-trust, ephemeral V8 isolate sandbox. This MCP setup ensures Vinkius does not store these scheduling details; they are sent directly to the API and wiped from the execution memory instantly.

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