Bring Staff Scheduling
to OpenAI Agents SDK
Learn how to connect 7shifts to OpenAI Agents SDK and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the 7shifts MCP Server?
Connect your 7shifts restaurant management account to any AI agent and simplify how you coordinate your workforce, manage shift assignments, and track labor costs through natural conversation.
What you can do
- Employee Management — List all staff members, create new employee profiles, and retrieve detailed metadata for individual users.
- Shift Coordination — Create, list, and monitor work assignments across different locations and departments.
- Schedule Oversight — List all work weeks (schedules) to understand your staffing coverage and planning.
- Labor Tracking — List actual time punches to monitor clock-in/out times and verify labor compliance.
- Organization Control — Query business locations, employee roles, and departments to manage your restaurant's structure.
- Operational Visibility — Check account status and monitor configured webhooks for real-time schedule events.
How it works
1. Subscribe to this server 2. Enter your 7shifts Company GUID and Token (found in your developer settings) 3. Start managing your restaurant team from Claude, Cursor, or any MCP clientWho is it for?
- Restaurant Managers — quickly retrieve staff lists and verify shift coverage via simple AI commands.
- Operations Teams — create new work assignments and monitor time clock entries directly from the workspace.
- Business Owners — get instant bird's-eye views of active shifts and team structure via the AI assistant.
Built-in capabilities (12)
Create a new employee
Create a new shift
Get my profile
Get employee details
List departments
List all employees
List business locations
List employee roles
List all schedules
List all shifts
List time clock entries
List active webhooks
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 12 tools from 7shifts through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries 7shifts, 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
7shifts in OpenAI Agents SDK
7shifts and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect 7shifts 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 7shifts in OpenAI Agents SDK
The 7shifts 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 12 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
7shifts for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the 7shifts MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I see all the active shifts for a specific employee via AI?
Yes! Use the list_shifts tool and provide the optional user_id. Your agent will retrieve the complete work history and future assignments for that specific person.
How do I create a new work shift using the agent?
Use the create_shift action. You'll need to provide the Location ID, and the start and end times in ISO 8601 format (e.g., 2024-12-01T10:00:00Z).
Is it possible to check real-time clock-in data via AI?
Absolutely. Use the list_time_punches query. The agent will retrieve the history of actual clock-in and clock-out events, allowing you to verify labor compliance instantly.
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.