How to Use the Doctolib MCP in Mastra AI

Q: How do I register the Doctolib MCP Server inside a Mastra AI agent?

Initialize the client using new MCPClient with the server URL. Then, call mcpClient.listTools() and spread those tools directly into your agent's tool configuration array.

Q: Can I require manual confirmation before booking a Doctolib appointment in Mastra AI?

Absolutely. Use the requireToolApproval check on the prendrerendezvous tool to pause execution and wait for patient confirmation before finalizing the slot.

Q: How does Mastra AI handle rate limits when polling Doctolib availabilities?

You configure the workflow's built-in backoff policy. If disponibilites hits a rate limit, the engine automatically backs off and retries according to your defined intervals.

Q: Can the agent search for doctors in specific cities?

Yes. The rechercherpraticiens tool filters directly by city boundaries, allowing the agent to locate nearby specialists without pulling unnecessary global listings.

Build resilient medical booking workflows in Mastra AI with automated retries and human-in-the-loop approvals using our Doctolib 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 Mastra AI

Create your Vinkius account to connect Doctolib to Mastra 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 Doctolib with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step Booking with Mastra AI and MCP Server

Medical scheduling is brittle. A slot visible a second ago might be gone when you try to book it. Mastra AI solves this by letting you build workflows that chain `disponibilites` and `prendre_rendez_vous` with built-in retry logic. If a booking attempt fails, the workflow engine automatically catches the error. It can fall back to searching other clinics using `lister_cabinets` without crashing the entire agent session.

Human Approval for Medical Appointments

You don't want an autonomous agent booking random doctors without confirmation. This MCP Server integrates with Mastra's `requireToolApproval` middleware. When the agent triggers `prendre_rendez_vous`, the workflow pauses and waits for a human to click confirm. While paused, the agent can display the selected practitioner's profile gathered from `consulter_praticien` and the specific reason retrieved via `motifs_consultation`. This keeps the patient in complete control of their calendar.

Dynamic Doctor Matching Workflows

Finding the right specialist requires smart filtering. Registering this MCP Server gives your Mastra AI agents direct access to `lister_specialites` to map the user's symptoms to an official medical field, then run `rechercher_praticiens` to find matching doctors in their city. Mastra's workflow engine handles these transitions as structured steps. If the first search returns no results, the agent branches to a wider geographical search automatically.

Setup guide

Set up Doctolib MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Doctolib tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "doctolib-mcp-client",
  servers: {
    "doctolib-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Doctolib Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Doctolib tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Doctolib transactions"
);
console.log(result.text);

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 Mastra AI

Initialize the client using `new MCPClient` with the server URL. Then, call `mcpClient.listTools()` and spread those tools directly into your agent's tool configuration array.

Absolutely. Use the `requireToolApproval` check on the `prendre_rendez_vous` tool to pause execution and wait for patient confirmation before finalizing the slot.

You configure the workflow's built-in backoff policy. If `disponibilites` hits a rate limit, the engine automatically backs off and retries according to your defined intervals.

Yes. The `rechercher_praticiens` tool filters directly by city boundaries, allowing the agent to locate nearby specialists without pulling unnecessary global listings.

No, this MCP Server runs in memory and does not log anything. All practitioner profiles and search queries are processed in memory through ephemeral sandboxed environments and instantly discarded.

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