Bring Medical Appointments
to OpenAI Agents SDK
Learn how to connect Doctolib to OpenAI Agents SDK and start using 8 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for Subscribers
What is the Doctolib MCP Server?
Connect your Doctolib partner account to any AI agent and take full control of your healthcare scheduling and practitioner research through natural conversation.
What you can do
- Practitioner Discovery — Search for doctors and specialists by specialty and city, identifying bounded office locations and member approximations natively
- Availability Tracking — Identify bounded routing spaces verifying absolute time availability slots attached directly matching the targeted doctor
- Appointment Management — List complex mappings evaluating exactly scheduled times and identifying physical reservations active within your account
- Live Booking — Commands the backend orchestrating real-time database locks inserting explicit reservation parameters structurally binding to an exact time slot
- Visit Motive Identification — Read available reason categories explicitly supported by a given Practitioner required for slot lock verification
- Practice Navigation — Perform structural extraction of localized entity bounds configuring the raw office locations active within the application
- Specialty Mapping — Enumerate explicitly attached structured roles defining valid medical specialties and practitioner targets globally
How it works
1. Subscribe to this server
2. Enter your Doctolib Partner API Key and API URL (e.g., https://api.doctolib.fr)
3. Start managing your healthcare appointments from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Patients — search for specialists and book appointments without navigating the web interface
- Healthcare Coordinators — manage schedules for multiple patients and verify doctor availability in real-time
- Medical Software Vendors — test and debug Doctolib integrations and appointment booking flows through natural conversation
- Administrative Assistants — audit scheduled visits and manage appointment logs using natural language
Built-in capabilities (8)
Consulter le profil d'un praticien
Vérifier les créneaux disponibles pour un praticien
Lister les cabinets médicaux
Lister les rendez-vous pris
Lister toutes les spécialités médicales disponibles
Lister les motifs de consultation d'un praticien
Prendre un rendez-vous médical
Restricts search to explicit city boundaries natively bypassing local lists. Rechercher des praticiens par spécialité et ville
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 8 tools from Doctolib through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Doctolib, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Doctolib in OpenAI Agents SDK
Doctolib and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Doctolib to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Doctolib in OpenAI Agents SDK
The Doctolib MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 8 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Doctolib for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Doctolib MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my agent search for specific medical specialists in a city?
Yes. Use the 'rechercher_praticiens' tool. Provide the specialty (e.g., 'médecin généraliste') and the city. The agent will retrieve matching practitioner profiles from Doctolib's active directory natively.
How do I book a consultation slot through the agent?
First, use 'disponibilites' to find free slots for a doctor. Then, provide the practitioner ID, the chosen slot ID, and your email to the 'prendre_rendez_vous' tool to confirm your reservation in the database.
Can I see all medical practices connected to my account?
Absolutely. Use the 'lister_cabinets' tool. Your agent will perform a structural extraction of localized entity bounds, showing you all physical office locations managed within your Doctolib partner environment.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.