Onfleet Connector for AI agents.
10 live capabilities
Manage last-mile delivery tasks and track driver locations in real time.
Waiting for input…
Why people use Onfleet
Onfleet for Real-Time Last-Mile Delivery Tracking
This Connector puts all those data points into one conversation. You can check a driver's status, update a delivery address, or pull a full day's history without ever leaving your AI client. It turns a messy dashboard into a clear set of commands.
What Vinkius changes
You get a command-line style interface for your entire delivery operation.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Handling a stuck delivery
A driver can't finish an order because the gate is locked.
- Real-world use case 02
Rapid order entry
A warehouse worker needs to book five deliveries at once.
- Real-world use case 03
Customer inquiry
A customer calls asking where their package is.
Complete set · 10capabilities
The complete Onfleet capability set.
These are the exact actions your AI can choose when you ask it to work with Onfleet.
01—04
4 capabilities in this set.
Part of 10 available through Onfleet.
- 01 Capability
Complete task override
Force-completes a delivery task when a driver can't finish it manually. This helps clear stuck orders quickly.
- 02 Capability
Create delivery task
Adds a new delivery to your fleet with a destination, recipient, and phone number. Use this to book new jobs.
- 03 Capability
Delete delivery task
Removes or archives a specific delivery task from your active list. This keeps your dashboard clean.
- 04 Capability
List tasks by date
Lists all deliveries within a specific date range for auditing or reporting. Great for end of day reviews.
05—07
3 capabilities in this set.
Part of 10 available through Onfleet.
- 05 Capability
Get worker schedule
Retrieves the specific shift times and availability for a single driver. Helps with planning daily routes.
- 06 Capability
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.
- 07 Capability
Update delivery task
Modifies the details of an existing delivery task like the recipient or address. Use this to fix order errors.
08—10
3 capabilities in this set.
Part of 10 available through Onfleet.
- 08 Capability
List dispatch hubs
Shows all your dispatch hubs including their geographic coordinates and zones. Useful for mapping your coverage.
- 09 Capability
Get task details
Pulls the specific data for one delivery task to see its current status. Use this for real-time tracking.
- 10 Capability
List fleet teams
Shows the different delivery teams organized within your Onfleet account. Use this to see your team structure.
Set up in minutes
One URL. Then ask Onfleet to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Onfleet from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_g0E06SpDZJptLH4anhCzCRgV7HK2vqU6ycFpQo5p/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Onfleet, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Onfleet for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_g0E06SpDZJptLH4anhCzCRgV7HK2vqU6ycFpQo5p/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Onfleet URL.
- Step 03
Save and start
Save the connection and enable Onfleet in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"onfleet": {
"url": "https://edge.vinkius.com/vk_preview_g0E06SpDZJptLH4anhCzCRgV7HK2vqU6ycFpQo5p/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Onfleet
Open Agent mode in chat and ask: "Using Onfleet, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"onfleet": {
"url": "https://edge.vinkius.com/vk_preview_g0E06SpDZJptLH4anhCzCRgV7HK2vqU6ycFpQo5p/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Onfleet
Ask Copilot: "Using Onfleet, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"onfleet": {
"url": "https://edge.vinkius.com/vk_preview_g0E06SpDZJptLH4anhCzCRgV7HK2vqU6ycFpQo5p/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Onfleet
Open Cascade and ask: "Using Onfleet, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"onfleet": {
"url": "https://edge.vinkius.com/vk_preview_g0E06SpDZJptLH4anhCzCRgV7HK2vqU6ycFpQo5p/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Onfleet
Ask Cline: "Using Onfleet, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add onfleet --transport http "https://edge.vinkius.com/vk_preview_g0E06SpDZJptLH4anhCzCRgV7HK2vqU6ycFpQo5p/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Onfleet
Ask Claude: "Using Onfleet, show me...". 10 tools are ready
Where the request belongs
Work Onfleet can move forward.
This is for the logistics lead who is tired of manual data entry and the support rep who is tired of asking drivers for status updates.
Logistics Manager
Monitors fleet performance and driver availability without jumping between different dashboards.
Dispatcher
Creates and updates delivery tasks on the fly to resolve exceptions in real time.
Customer Support
Looks up delivery IDs to give customers instant ETAs and driver locations.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsShipday
Dispatch and track local deliveries with driver management, route optimization, and real-time tracking for last-mile operations.
DROPBOY
Equip your AI agent to manage logistics orders, track fleet vehicles, and monitor delivery drivers via the DROPBOY API.
Track-POD
Optimize delivery routes, capture electronic proof of delivery, and track driver performance for logistics operations.
MotionTools
Manage logistics and delivery operations via MotionTools. track bookings, drivers, and vehicles directly from your AI agent.
OptimoRoute
Optimize delivery routes via OptimoRoute. create orders, track driver locations, and manage route planning directly from any AI agent.
Bringg
Automate final-mile logistics via Bringg. manage delivery tasks, track fleets, and assign drivers directly from your AI agent.
Bring your own AI
Change the model, client or framework. Keep Onfleet connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Onfleet.
The practical details behind the request, access and result.
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.
One connection away
Give your agent a direct line to Onfleet.
Connect Onfleet once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available