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.

Onfleet MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Onfleet
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Onfleet through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Onfleet Assistant",
            instructions=(
                "You help users interact with Onfleet. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Onfleet"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Onfleet MCP Server

Connect your Onfleet delivery operations to any AI agent and run your fleet from a single conversation.

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.

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

The Onfleet MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Onfleet to OpenAI Agents SDK via MCP

Follow these steps to integrate the Onfleet MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Onfleet

Why Use OpenAI Agents SDK with the Onfleet MCP Server

OpenAI Agents SDK provides unique advantages when paired with Onfleet through the Model Context Protocol.

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 + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Onfleet MCP Server delivers measurable value.

Automated workflows: build agents that query Onfleet, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Onfleet, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Onfleet tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Onfleet to resolve tickets, look up records, and update statuses without human intervention

Onfleet MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Onfleet to OpenAI Agents SDK via MCP:

complete_task_override

Force-complete a delivery task

create_delivery_task

Create a new delivery task in Onfleet

delete_delivery_task

Delete/Archive a delivery task

get_task_details

Get details for a specific delivery task

get_worker_schedule

Get a driver's work schedule

list_dispatch_hubs

List all dispatch hubs

list_fleet_teams

List all delivery teams

list_fleet_workers

List all fleet drivers/workers

list_tasks_by_date

List delivery tasks within a date range

update_delivery_task

Update an existing delivery task

Example Prompts for Onfleet in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Onfleet immediately.

"Create a delivery task to 123 Main St, San Francisco for John Doe with phone 415-555-0100."

"Show me all deliveries from yesterday with their status."

"Which drivers are online right now and how many active tasks does each have?"

Troubleshooting Onfleet MCP Server with OpenAI Agents SDK

Common issues when connecting Onfleet to OpenAI Agents SDK through the Vinkius, and how to resolve them.

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.

Onfleet + OpenAI Agents SDK FAQ

Common questions about integrating Onfleet MCP Server with OpenAI Agents SDK.

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.