# Onfleet MCP for AI Agents AI Agent Connect > Onfleet MCP lets you manage last-mile deliveries through your AI agent. You can create tasks, track active drivers in real time, pull shift schedules, and audit delivery history without switching tabs. It is built for logistics teams who need to move orders faster. ## Overview - **Category:** erp-operations - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_g0E06SpDZJptLH4anhCzCRgV7HK2vqU6ycFpQo5p/ai-agent-connect - **Tags:** last-mile-delivery, route-optimization, fleet-tracking, dispatch, proof-of-delivery, real-time-logistics ## Description Managing a delivery fleet usually means having twenty tabs open at once. You are constantly jumping between a dashboard to see where a driver is, a spreadsheet to check schedules, and an email thread to handle a customer inquiry about a package location. It is exhausting and leads to mistakes when you are trying to move hundreds of packages a day. This Connector changes that by bringing the entire Onfleet operation into your AI client. Instead of hunting for data, you just ask your agent to find a specific delivery or check a driver's capacity. You can create new tasks with full recipient details, update order statuses, or force-complete a delivery that got stuck in the system. It is about having a single point of contact for your logistics. Since Vinkius hosts this Connector, you can plug it into your existing workflow and start dispatching from one conversation. It handles the heavy lifting of querying your fleet's data so you can focus on getting the goods to the right people on time. ## Tools ### complete_task_override Force-completes a delivery task when a driver can't finish it manually. This helps clear stuck orders quickly. ### create_delivery_task Adds a new delivery to your fleet with a destination, recipient, and phone number. Use this to book new jobs. ### delete_delivery_task Removes or archives a specific delivery task from your active list. This keeps your dashboard clean. ### list_tasks_by_date Lists all deliveries within a specific date range for auditing or reporting. Great for end of day reviews. ### get_worker_schedule Retrieves the specific shift times and availability for a single driver. Helps with planning daily routes. ### list_fleet_workers Provides a full list of all drivers and workers currently in your fleet. Use this to see who is on the clock. ### update_delivery_task Modifies the details of an existing delivery task like the recipient or address. Use this to fix order errors. ### list_dispatch_hubs Shows all your dispatch hubs including their geographic coordinates and zones. Useful for mapping your coverage. ### get_task_details Pulls the specific data for one delivery task to see its current status. Use this for real-time tracking. ### list_fleet_teams Shows the different delivery teams organized within your Onfleet account. Use this to see your team structure. ## Prompt Examples **Prompt:** ``` I have a new delivery for 500 Oak St. Can you add it to the system? ``` **Response:** ``` I've created that delivery task for you. It's now in the queue for assignment. Would you like me to check which drivers are nearest to Oak St? ``` **Prompt:** ``` Which drivers are currently busy with deliveries? ``` **Response:** ``` Here is the current status of your active fleet: | Driver | Active Tasks | Status | | :--- | :--- | :--- | | Maria Chen | 3 | In Transit | | Alex Rivera | 6 | At Capacity | | Tom Wilson | 1 | Available | Would you like me to see the schedule for any of these drivers? ``` **Prompt:** ``` Show me the delivery history from last Tuesday. ``` **Response:** ``` I found 32 deliveries from last Tuesday. * **Completed**: 28 * **Failed**: 3 (Address issues) * **Cancelled**: 1 Would you like to see the specific details for the 3 failed deliveries? ``` ## Capabilities ### Create delivery tasks Generate new orders with addresses and recipient info. ### Track fleet status See which drivers are online and what they are currently carrying. ### Pull driver schedules View specific shift times and availability for any worker. ### Audit task history Query past deliveries by date to see what succeeded or failed. ### Manage dispatch hubs Browse your team structure and geographic zone coverage. ## Use Cases ### Handling a stuck delivery A driver can't finish an order because the gate is locked. The dispatcher asks the agent to use complete_task_override to clear the task. ### Rapid order entry A warehouse worker needs to book five deliveries at once. They tell the agent to use create_delivery_task for each new order. ### Customer inquiry A customer calls asking where their package is. The support agent uses get_task_details to give a live ETA. ### Shift planning A manager wants to see who's working tomorrow. They ask the agent to use get_worker_schedule for all drivers. ## Benefits - Stop switching tabs by accessing your entire Onfleet fleet directly through your AI client. - Speed up order processing by using create_delivery_task to add new jobs with one command. - Resolve delivery issues faster with complete_task_override to clear stuck orders instantly. - Get instant answers for customers by using get_task_details to see live driver locations. - Simplify reporting by using list_tasks_by_date to pull history for any specific day or week. - Know your team's capacity by using list_fleet_workers to see who is online and who is busy. ## How It Works The bottom line is you get a command-line style interface for your entire delivery operation. 1. Subscribe to the Onfleet MCP on Vinkius. 2. Paste your Onfleet API Key into your client settings. 3. Start asking your agent to create tasks or check driver locations. ## Frequently Asked Questions **How can I use the Onfleet MCP to manage my deliveries?** You can use your AI client to create, update, and complete delivery tasks directly through a conversation. This lets you handle your daily dispatching without having to log into the Onfleet dashboard every few minutes. **Can the Onfleet MCP help me track my drivers in real time?** Yes. You can ask your agent to check which drivers are currently online and see their active task loads. This gives you a quick pulse on your fleet's status at any moment. **Does the Onfleet MCP work with Claude or Cursor?** Yes, it works with any MCP-compatible client, including Claude, Cursor, and Windsurf. Once connected via Vinkius, your agent can access all your Onfleet data. **How do I create new delivery tasks using the Onfleet MCP?** Just tell your AI agent the delivery details, like the address and recipient name. It will use the Connector to generate the task in Onfleet and confirm the tracking ID for you. **Can I see my fleet's shift schedules with the Onfleet MCP?** You can ask your agent to pull the specific work schedules for any driver in your fleet. It will return their shift times and availability windows instantly. **Can the Onfleet MCP help with customer support inquiries?** Absolutely. Support teams can ask the agent to look up a specific delivery ID to get real-time ETAs and driver locations to give customers accurate updates. **How do I audit my delivery history using the Onfleet MCP?** You can ask your agent to list all deliveries from a specific date range. It will pull the history so you can review completed, failed, or pending orders for your reports. **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.