How to Use the Doctolib MCP in Vercel AI SDK

Q: How do I handle user authentication inside Vercel AI SDK using this Doctolib MCP Server?

You use the authProvider option when setting up your createMCPClient. This passes the patient's secure OAuth token directly, allowing tools like listerrendezvous to fetch their specific history safely.

Q: What is the best way to handle booking errors with Doctolib and Vercel AI SDK?

When prendrerendezvous fails due to a taken slot, the SDK streams the error back to the model. Your agent can immediately call disponibilites to offer alternative slots to the user in the same chat session.

Q: Do I need to manually configure endpoints for every clinic location?

No. The listercabinets tool automatically returns all associated locations for a doctor. Your agent parses this list and lets the user choose their preferred location before booking.

Render live Doctolib booking slots and practitioner search results directly in your Next.js UI using Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Doctolib MCP to Vercel AI SDK

Create your Vinkius account to connect Doctolib 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 Doctolib with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Practitioner Search in React

Stop making users wait for heavy background API calls to resolve. This integration feeds the `rechercher_praticiens` tool directly into your streaming UI, letting patients see matching doctors pop up on the screen in real-time. By coupling Vercel AI SDK with this MCP Server, your interface renders practitioner profiles instantly using `consulter_praticien` as the model fetches them. You initialize the connection with `createMCPClient` and pass the tools directly to `streamText`. This bypasses traditional API glue code entirely, feeding structured Doctolib physician data straight to your custom React components.

Real-time Slot Selection with MCP Server

Checking doctor availability shouldn't feel like a guessing game. Your Vercel AI SDK client calls `disponibilites` to grab open slots and displays them instantly in the chat window. Users click a slot, and the client triggers `prendre_rendez_vous` to lock it in. Because the Vercel AI SDK runs on edge functions, these calls happen with minimal latency. This MCP Server handles the heavy lifting of fetching `motifs_consultation` so your users only see valid options for their specific medical needs.

Clean Session Lifecycle Management

Security matters when handling healthcare schedules. This setup uses the Vercel AI SDK `authProvider` config to manage user OAuth sessions safely. Once the model finishes listing past bookings with `lister_rendez_vous`, you call `mcpClient.close()` to tear down the connection. This keeps your edge runtime clean and prevents memory leaks. You get a secure, ephemeral connection that talks to Doctolib only when your user is actively interacting with the UI.

Setup guide

Set up Doctolib 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 Doctolib 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 Doctolib 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 Doctolib. 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 Doctolib 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 Doctolib MCP in Vercel AI SDK

You use the `authProvider` option when setting up your `createMCPClient`. This passes the patient's secure OAuth token directly, allowing tools like `lister_rendez_vous` to fetch their specific history safely.

Yes, this MCP Server is fully compatible with Vercel AI SDK stream rendering. By passing the tools from `mcpClient.tools()` to `streamText`, the model invokes `consulter_praticien` and streams the JSON structured doctor profile straight to your frontend UI components.

When `prendre_rendez_vous` fails due to a taken slot, the SDK streams the error back to the model. Your agent can immediately call `disponibilites` to offer alternative slots to the user in the same chat session.

No. The `lister_cabinets` tool automatically returns all associated locations for a doctor. Your agent parses this list and lets the user choose their preferred location before booking.

The server runs in a zero-trust V8 Isolate sandbox, meaning no medical appointments or scheduling details are stored on our servers. Your patient's private details go directly from the client to the medical platform over encrypted transit.

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