99Minutos Express MCP for AI. Dispatch couriers, quote rates, and track packages instantly.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
99Minutos Express connects your AI client directly to a physical courier network, treating it like a dispatch terminal for Latin American e-commerce logistics.
It lets you get instant point-to-point shipping quotes between zip codes and automatically trigger real-world pickup missions through natural language commands.
What your AI can do
Cancel order
Voids an existing, active courier pickup mission.
Create order
Requests a new express delivery service between two points.
Create store
Registers a brand new local dispatch warehouse or node location.
Input two zip codes and receive a calculated cost for express or next-day delivery services.
Trigger a live courier service request simply by specifying the target location in natural language.
Pull current GPS data to see exactly where an active vehicle is at any given moment.
Verify if specific geographical bounds are currently within the courier's active service grid.
View, list, or cancel both outgoing shipments and reverse logistics (returns).
Ask an AI about this
Waiting for input…
99Minutos Express: 12 Logistics Tools
Use these twelve tools to handle every step of the last-mile logistics cycle, from quoting initial rates to tracking final delivery.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using 99Minutos Express on VinkiusCancel Order
Voids an existing, active courier pickup mission.
Create Order
Requests a new express delivery service between two points.
Create Store
Registers a brand new local dispatch warehouse or node location.
Create Webhook
Sets up an HTTP endpoint to receive automated delivery status updates.
Get Order
Retrieves the detailed status and history for a specific express order number.
Get Rates
Checks the cost to move goods between any two specified zip codes on the same day.
Get Tracking
Pulls live, real-time GPS coordinates for a package currently in transit.
List Coverage
Checks the operational service range and coverage status of various LatAm zip codes.
List Orders
Pulls a list of all active, currently running express orders in one area.
List Return Orders
Shows the status and details for goods coming back to the store (reverse logistics).
List Stores
Lists all registered physical dispatch nodes or warehouses.
List Webhooks
Scans and reports on the active webhook endpoints set up for system communication.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with 99Minutos Express, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by 99Minutos App. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Tracking logistics costs used to be a mess of manual rate sheets and API calls.
Before this MCP, figuring out shipping costs meant logging into separate carrier portals or maintaining complex spreadsheets. You'd have to manually input the origin zip code, then the destination zip code, hit submit, copy the quote, and repeat that process for every single sale.
Now, you simply tell your agent what needs doing in plain language. The MCP handles all the backend work, giving you an instant cost estimate from `get_rates` right where you're working. It just works.
Dispatching a pickup is now as simple as speaking to it.
You used to have to write custom backend code, manage credentials for the dispatch API, and structure your requests perfectly—all just to tell a truck where to go. That was complex setup, every time.
Today, you bypass the code entirely. You ask your agent to initiate the run, and it triggers `create_order` instantly. The complexity of the logistics network disappears into a simple chat command.
What your AI can actually do with this
This MCP transforms your AI agent from a simple chatbot into a heavy dispatcher terminal. Instead of manually jumping between carrier websites to estimate costs, you feed two zip codes, and the system instantly calculates exactly what it takes to move goods via Express or Next-Day services across LatAm.
The core loop is dispatching: write a request like 'Call a courier delivering at XYZ,' and your agent executes that as a real pickup mission. You can manage the entire lifecycle, from checking if a zone is even covered using list_coverage to tracking a package in real time with get_tracking.
This kind of deep logistical integration was previously locked behind complex API keys or manual web scraping. Now, Vinkius makes it available through one simple connection, letting you handle everything right from your chat interface.
019d845f-f00e-71ef-be6e-de592a8e21b8 Here's how it actually works
The bottom line is you talk to your agent like talking to a logistics coordinator; it handles all the underlying API calls.
Install the node mapping within your environment.
Fetch your 99 API Bearer Code by extracting it from the merchant layout.
Use natural phrases to tell the AI client what needs doing, and the MCP translates that into a physical dispatch command.
Who is this actually for?
This connector is for operational roles that live in e-commerce and supply chain. You’re the D2C store operator who needs real-time dispatching without relying on flaky third-party apps, or the logistics engineer tracking failure rates across massive territories.
Needs to compare costs and determine if a sale is viable by running instant rate checks (get_rates) before confirming an order.
Manages daily pickups, creating new orders using create_order or canceling failed runs with cancel_order on the fly.
Consolidates data to look at metrics like delivery failure rates and active run performance across different nodes (list_orders, list_return_orders).
What Changes When You Connect
Stop guessing costs. Use get_rates to get an immediate cost estimate for any point-to-point delivery run before you even commit to the sale.
Automate dispatching. Instead of writing code to trigger pickups, just ask your agent to 'Call a courier...' and use create_order to execute it.
Eliminate tracking blind spots. Use get_tracking to pull live GPS updates, knowing exactly if a package is delayed or on time.
Scale logistics coverage. Before accepting an order, run list_coverage to confirm the zip code falls within the current active service grid.
Simplify post-sale ops. Manage both outgoing shipments and incoming returns by listing all necessary items via list_orders and list_return_orders.
See it in action
A customer asks for shipping cost estimates
The agent receives a request: 'How much does it cost to send this product from 14002 to 16003?' The system uses get_rates immediately, providing the client with an accurate quote and allowing the user to proceed directly to creating the sale.
A shipment goes missing or is delayed
The operations manager inputs the order ID. The agent calls get_tracking, pulling real-time data that shows the package moved out of a local hub thirty minutes ago, giving them an immediate status update and ETA.
Managing post-sale returns
A customer sends back a faulty item. Instead of manual logging, the agent runs list_return_orders, showing the entire history and current location of the returned goods for processing.
The honest tradeoffs
Assuming universal coverage
Just checking if a zip code is 'in range' without knowing if it's actually served by the courier.
Always run list_coverage first. This confirms the zone is active before you waste time calling get_rates.
Forgetting to list all shipments
Trying to find an order status but forgetting which specific ID or type of shipment was created.
Use list_orders and list_return_orders together. This gives you a complete view of every active logistics movement.
Leaving old services running
A dispatch mission fails, but the system thinks it's still active, leading to duplicate billing or confusion.
Always confirm status and use cancel_order if a pickup mission is voided or failed before starting a new one.
When It Fits, When It Doesn't
Use this MCP if your primary need is immediate, actionable logistics: calculating real-time costs between two specific points, dispatching goods right now, or tracking an active parcel. It's built for the 'what happens next' moment.
Don't use it if you are only trying to map out potential market expansion into completely unserved regions (that requires a different kind of data source). Also, don't rely on this solely for reading historical metrics; while list_orders helps, dedicated analytics tools are better for long-term trend analysis. If your goal is just general business mapping rather than live dispatching, check the documentation for alternative GIS services.
Questions you might have
How do I check if my desired zip code is covered using list_coverage? +
You run list_coverage and provide your specific ZIP codes. The tool responds by confirming if those bounds fall within the courier's currently active service grid.
Is there a way to see all my current shipments with list_orders? +
Yes, running list_orders pulls a comprehensive list of every active express order in your area. This is useful for quick inventory checks and status overviews.
What if I need to stop an order that was just created using cancel_order? +
Use cancel_order with the relevant order ID. The tool voids the active courier run, preventing further charges or dispatch efforts for that specific mission.
Can I check real-time location data using get_tracking? +
Absolutely. get_tracking pulls live GPS coordinates for a package on its way to you, giving you the most current status and estimated arrival time.
When using `get_rates`, what are the requirements for calculating costs between multiple points? +
The tool requires a structured list of coordinates or postal codes. You must pass all start and end points in a single request payload, not one by one. This allows you to calculate complex multi-stop routes instantly.
How do I monitor the status of returned items using `list_return_orders`? +
This tool shows all reverse logistics flows and returns. You can filter results by return date or original order ID to track where the package is in the return process.
What do I need to know when using `create_store` to register a new dispatch warehouse? +
You must provide the physical address, operational hours, and necessary local permits for the node. This registers the location in our network so it can accept courier pickups.
If my automated system fails to receive status updates, how do I use `list_webhooks`? +
Use this tool to audit all active HTTP delivery ping receptors. It lists the endpoints and their last successful trigger time, helping you verify if your integration is running.
Are the pickup locations visible if I list coverage endpoints openly? +
No. The system protects sensitive core nodes. Also, the primary Bearer Token connecting the logistic grid behaves with absolute sensitive: true markings eliminating API key peeking internally or across screen sharing software.
Is it possible to estimate costs exclusively without mistakenly dispatching a live courier? +
Definitely! Estimations are securely isolated using exclusively the get_rates endpoint. This acts as an inert sandbox fetching pure monetary quotes based on dimensions without generating 'Orders'. Live dispatch strictly requires create_order action flags limiting accidental triggers.
Can I add multiple webhooks? +
Yes, via the agent.
We've already built the connector for 99Minutos Express. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.