How to Use the Doodle MCP in Vercel AI SDK

Q: How do I stream Doodle poll results using Vercel AI SDK and MCP?

Use streamText along with the getpoll tool to fetch the raw scheduling data. Your React frontend receives the poll structure as a live stream, rendering the options immediately as they load.

Q: Can Vercel AI SDK close a Doodle poll automatically?

Yes. Your agent evaluates participant preferences from listparticipants and calls closepoll to set the final date. This update streams directly to your Next.js UI components.

Q: How does Vercel AI SDK handle Doodle participant updates?

The SDK executes addparticipant when a user selects their preferred times in your chat interface. It pushes the preference array to the API and streams the updated participant count back to the UI.

Q: What happens if a user deletes a poll?

The agent triggers deletepoll to wipe the scheduling data from the system. Your frontend UI immediately reflects this empty state by clearing the active scheduling cards.

Use Vercel AI SDK to stream real-time Doodle poll creation and participant updates directly into your React or Next.js frontend.

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 Vercel AI SDK

Create your Vinkius account to connect Doodle to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Doodle Polls to Your Vercel AI SDK UI

The `create_poll` tool generates group scheduling polls directly inside your Vercel AI SDK chat interface via our MCP Server. Your frontend displays these scheduling options to users without making them wait for a full page reload or API roundtrip. When your Next.js app calls `list_polls`, the raw JSON feeds straight into your streaming components. This keeps your users engaged because they watch the scheduling choices build on screen in real-time.

Interactive Participant Voting in Edge Functions

The `add_participant` tool records user availability preferences directly from lightweight edge-rendered UI components using this MCP integration. This Vercel AI SDK integration handles instant voting without the latency of traditional server setups. If a user changes their mind, your streaming interface triggers `remove_participant` to update the counts instantly. The edge function executes the update and immediately streams the corrected options back to the client browser.

Direct Thread Commenting and Closing

The `add_comment` tool appends feedback directly to active scheduling sheets within your Vercel AI SDK chat view. Users read and write to the discussion thread while the conversational agent processes their scheduling requests. Once the team reaches a consensus, the agent calls `close_poll` to lock in the winning time slot. Your React components update instantly to show the final selected schedule without requiring manual page refreshes.

Setup guide

Set up Doodle MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Doodle tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Doodle transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use streamText along with the `get_poll` tool to fetch the raw scheduling data. Your React frontend receives the poll structure as a live stream, rendering the options immediately as they load.

Yes. Your agent evaluates participant preferences from `list_participants` and calls `close_poll` to set the final date. This update streams directly to your Next.js UI components.

The SDK executes `add_participant` when a user selects their preferred times in your chat interface. It pushes the preference array to the API and streams the updated participant count back to the UI.

The agent triggers `delete_poll` to wipe the scheduling data from the system. Your frontend UI immediately reflects this empty state by clearing the active scheduling cards.

Your Doodle poll, participant, and comment data stay protected because Vinkius runs this MCP Server in an isolated V8 sandbox. Your API tokens are encrypted, and data only passes through ephemeral execution environments.

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