How to Use the Doodle MCP in Pydantic AI

Q: How do I connect Pydantic AI to the Doodle MCP Server?

Use the MCPToolset constructor with your Vinkius HTTP endpoint URL. Pass this toolset into your Agent instance to make tools like createpoll and getpoll available to your Python models.

Q: Can I use Pydantic AI to clean up inactive Doodle polls?

Yes, your agent can query inactive entries with listpolls and programmatically call deletepoll to remove them. The type-safe environment ensures you only delete the exact poll IDs targeted by your logic.

Run type-safe Doodle scheduling workflows in Pydantic AI with strict runtime schema validation for every vote and comment.

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 Pydantic AI

Create your Vinkius account to connect Doodle to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Doodle poll creation via MCP Server

This MCP Server exposes `create_poll` with strict type validation to ensure your Pydantic AI agent never sends malformed Doodle scheduling requests. If the Pydantic AI agent attempts to pass an invalid Doodle option format, the SDK blocks the call before it hits the network. By calling `list_polls`, your Pydantic AI agent retrieves a typed list of active Doodle schedules. The framework validates the returned fields against Pydantic models, preventing silent Doodle data corruption if the API payload changes.

Strict validation for Doodle participant votes

Use the `add_participant` tool in Pydantic AI to enforce correct formatting on Doodle preference arrays. The Pydantic framework guarantees that the numbers matching your Doodle options (0, 1, or 2) conform strictly to the expected schema before submitting. If a user needs to change their selection, the Pydantic AI agent runs `remove_participant` to update the Doodle poll. This ensures your local application state remains synchronized with Doodle without manual parsing.

Structured comment and finalization flows

The `add_comment` tool allows your Pydantic AI agent to attach structured feedback to any Doodle poll. Because the Doodle comments are validated on retrieval via `get_comments`, your downstream Pydantic data processors can safely assume clean string structures. When closing the Doodle poll, the Pydantic AI agent uses `close_poll` to commit the final winning option. The Pydantic system validates the final string against the original Doodle poll options, ensuring you never finalize a meeting on a non-existent date.

Setup guide

Set up Doodle MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "doodle-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Doodle tools.",
)

result = await agent.run("List recent Doodle transactions")
print(result.output)

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 Pydantic AI

Use the `MCPToolset` constructor with your Vinkius HTTP endpoint URL. Pass this toolset into your `Agent` instance to make tools like `create_poll` and `get_poll` available to your Python models.

The framework fails loudly by raising a validation error. This prevents your agent from making decisions based on corrupted poll structures or missing participant fields.

Yes, your agent can query inactive entries with `list_polls` and programmatically call `delete_poll` to remove them. The type-safe environment ensures you only delete the exact poll IDs targeted by your logic.

Yes, the toolset integrates directly with Pydantic AI's async execution loop. Your agent can fetch comments via `get_comments` and add votes via `add_participant` concurrently without blocking your main application.

Your poll configurations, participant names, and comments are processed entirely in memory within an ephemeral MCP sandbox. No scheduling details are written to persistent storage, ensuring zero data leakage during agent execution.

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