Bring Last Mile Delivery
to OpenAI Agents SDK
Create your Vinkius account to connect Onfleet to OpenAI Agents SDK and start using all 10 AI tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code. No hosting, no server setup — just connect and start using.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Onfleet MCP Server?
Connect your Onfleet delivery operations to any AI agent and run your fleet from a single conversation.
What you can do
- Delivery Tasks — Create, update, delete, and force-complete delivery tasks with full address and recipient details
- Fleet Tracking — List all active drivers, check who's online, and view their assigned capacities in real time
- Driver Schedules — Pull exact shift times and availability windows for any worker in your fleet
- Teams & Hubs — Browse your team structure and dispatch hubs with geographic coordinates and zone coverage
- Task History — Query tasks by date range to audit completed, failed, or pending deliveries across your operation
How it works
- Subscribe to this server
- Enter your Onfleet API Key
- Start dispatching and tracking deliveries from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Logistics managers — monitor fleet performance and driver availability without switching between dashboards
- Ops teams — create and update delivery tasks on the fly, resolve exceptions, and force-complete stuck orders
- Customer support — look up any delivery by ID to get real-time ETA and driver location for customer inquiries
Built-in capabilities (10)
Force-complete a delivery task
Create a new delivery task in Onfleet
Delete/Archive a delivery task
Get details for a specific delivery task
Get a driver's work schedule
List all dispatch hubs
List all delivery teams
List all fleet drivers/workers
List delivery tasks within a date range
Update an existing delivery task
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 10 tools from Onfleet through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Onfleet, 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
Onfleet in OpenAI Agents SDK
Why run Onfleet with Vinkius?
The Onfleet connection runs on our fully managed, secure cloud infrastructure. We handle the hosting, maintenance, and security so you don't have to deal with servers or code. All 10 tools are ready to work instantly without any complex setup.
You stay in complete control of your data. Your AI only accesses the information you approve, keeping your sensitive passwords and private details completely safe. Plus, with automatic optimizations, your AI works faster and more efficiently.
* Every connection is hosted and maintained by Vinkius. We handle the security, updates, and infrastructure so you don't have to write code or manage servers. See our infrastructure
Over 4,000 integrations ready for AI agents
Explore a vast library of pre-built integrations, optimized and ready to deploy.
Connect securely in under 30 seconds
Generate tokens to authenticate and link external services in a single step.
Complete visibility into every agent action
Audit live requests, latency, success rates, and active security compliance policies.
Optimize spending and track token ROI
Analyze real-time token consumption and cost metrics detailed by connection.
Explore our live AI Agents Analytics dashboard to see it all working
This dashboard is included when you connect Onfleet using Vinkius. You will never be left in the dark about what your AI agents are doing with your tools.
Onfleet and 4,000+ other AI tools. No hosting, no code, ready to use.
Professionals who connect Onfleet to OpenAI Agents SDK through Vinkius don't need to write code, manage servers, or worry about security. Everything is pre-configured, secure, and runs automatically in the background.
Raw MCP | Vinkius | |
|---|---|---|
| Ready-to-use MCPs | Find and configure each manually | 4,000+ MCPs ready to use |
| Connection Setup | Manual coding & server setup | 1-click instant connection |
| Server Hosting | You host it yourself (needs 24/7 uptime) | 100% hosted & managed by Vinkius |
| Security & Privacy | Stored in plaintext config files | Bank-grade encrypted vault |
| Activity Visibility | Blind execution (no logs or tracking) | Live dashboard with real-time logs |
| Cost Control | Runaway AI token spend risk | Automatic budget limits |
| Revoking Access | Must delete files or code to stop | 1-click disconnect button |
How Vinkius secures
Onfleet for OpenAI Agents SDK
Every request between OpenAI Agents SDK and Onfleet is protected by our secure gateway. We automatically keep your sensitive data private, prevent unauthorized access, and let you disconnect instantly at any time.
Frequently asked questions
Can my AI agent create a complete delivery task with address and recipient?
Yes. Pass a JSON object with destination address, recipient name, phone, and any notes — the agent calls the Onfleet Tasks API and returns the created task with its tracking ID. You can also update or delete tasks the same way.
How does force-completing a task differ from a normal driver completion?
Force-completing bypasses the driver app flow — useful when a delivery was made but the driver forgot to mark it done, or for admin overrides. The agent sends the completion details (success/failure and notes) directly to the Onfleet API, updating the task status without driver interaction.
Can I see which drivers are online right now and their schedules?
Yes. List all workers to see their online/offline status, active task count, and current location. Then query any specific worker's schedule to see their shift times and availability windows. Perfect for capacity planning and real-time dispatch decisions.
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.
Explore More MCP Servers
View all →
FOIA.gov (Freedom of Information)
4 toolsAccess US government FOIA data — list agency components, retrieve request forms, and fetch annual reports directly from FOIA.gov.
World Bank Education & Health
5 toolsRetrieve global life expectancy, infant mortality, literacy rates, and social welfare statistics without any authentication.
Everfit Coaching
10 toolsEquip your AI agent to manage coaching clients, track workout plans, and monitor performance via the Everfit API.
DISQO
10 toolsEquip your AI agent to manage consumer insight projects, track audiences, and monitor behavioral metrics via the DISQO API.