Shansong Swift Delivery MCP for AI. Track live GPS, calculate fees, and dispatch orders automatically.

Q: How do I get live tracking using queryriderposition?

You pass an order ID to queryriderposition. This tool returns the real-time GPS coordinates (Latitude and Longitude) of the assigned driver, allowing your agent to provide precise updates.

Q: Do I need to calculate fees before creating an order using calculatefee?

Yes. Always run calculatefee first. This confirms the current rates and total cost for the route. It’s best practice to validate pricing before you call createorder.

Q: What if I need to cancel a delivery, what tool do I use?

Use cancelorder. This tool sends the cancellation payload to Shansong's system. It handles stopping the dispatch and updating the status internally.

Q: How do I submit a complaint against a driver?

Call the submitcomplaint tool directly. You provide necessary details, and the server submits an official record of the issue to Shansong's system for review.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Shansong Swift Delivery MCP Server connects your AI agent directly into Shansong's P2P logistics network. It lets you estimate delivery routes, dispatch riders instantly, and track live GPS locations for any order.

Use it to manage the entire last-mile process without touching a dashboard.

What your AI can do

Add tip

Adds a monetary tip to encourage a driver to pick up an order faster.

Calculate fee

Determines the final cost of a delivery route before placing an official order.

Cancel order

Stops a live delivery dispatch that needs to be canceled for any reason.

+ 7 more capabilities included

Track Rider Location

Gets live GPS coordinates of the Shansong rider assigned to an order.

Estimate Delivery Costs

Calculates the total fee for a delivery route before dispatching an order.

Create New Deliveries

Submits a complete, actionable new Shansong delivery order payload.

Manage Order Status

Retrieves the live status details for any existing order ID.

Dispatch Commands

Can cancel a dispatch, confirm goods pickup, or add tips to incentivize the rider.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Shansong Swift Delivery: 10 Tools for Logistics

Manage every stage of the delivery lifecycle—from estimating costs to tracking real-time rider movement—using these ten specialized tools.

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 Shansong Swift Delivery on Vinkius

Add Tip

Adds a monetary tip to encourage a driver to pick up an order faster.

Calculate Fee

Determines the final cost of a delivery route before placing an official order.

Cancel Order

Stops a live delivery dispatch that needs to be canceled for any reason.

Confirm Goods

Marks the shipment as successfully picked up from the origin location.

Create Order

Generates and submits a brand new delivery order into the Shansong network.

Query City List

Fetches a list of all active cities where Shansong currently operates services.

Query Order Info

Retrieves the current, live status and details for an existing order ID.

Query Rider Position

Gets real-time GPS coordinates of the assigned Shansong rider.

Query Store List

Lists all available stores within a specific city for routing purposes.

Submit Complaint

Submits an official complaint against the assigned rider through the system.

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.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Shansong Swift Delivery integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "shansong-swift-delivery": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Shansong Swift Delivery tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"shansong-swift-delivery": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

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

Start building

Make Your AI Do More

Start with Shansong Swift Delivery, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ 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

Shansong Swift Delivery MCP server cover

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Shansong. 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

Your data is protected. See how we built it.

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 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Customer support usually means endless clicks and confusing status pages.

Today, answering 'Where is my order?' requires the agent to log into the Order Dashboard, search by ID, wait for the page to load, read out a vague status (e.g., 'In Transit'), and then potentially open a separate map link—all while the customer waits on hold or in chat.

With this MCP server, your AI client handles it instantly. You just pass the order ID to `query_order_info`. The agent pulls the live status, verifies the last known location using `query_rider_position`, and gives a precise, actionable update—no dashboards involved.

The Shansong Swift Delivery MCP Server: Full control over dispatching.

Manual dispatch requires someone to first check the pricing structure, then manually fill out a form with all parameters (items, addresses), and finally hit 'Submit.' Mistakes here mean lost revenue or failed deliveries.

Now, your agent executes this entire process cleanly. It calls `calculate_fee` for validation, submits the payload via `create_order`, and you're done. The system handles the complexity; you just manage the intent.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Shansong Swift Delivery MCP Server connects your AI agent straight into Shansong’s Point-to-Point logistics network. It handles the whole last mile—you don't gotta touch any dashboards, you just tell your agent what needs doing. You can manage everything from figuring out costs to tracking where that rider is right now.

To get started, you first need to know where Shansong operates; use query_city_list to pull up every active city they service. When you're planning a route, you gotta check the local stops; running query_store_list lets your agent list all available stores within a specific area for precise routing purposes. Before generating anything, you run calculate_fee to determine the final cost of a delivery route.

This confirms the budget before you commit.

Ready to send it out? You use create_order to generate and submit a brand new delivery order payload into the Shansong network. Once that's done, your agent can mark the goods as officially picked up from the origin point by executing confirm_goods. If things change fast—say, you need to stop the dispatch for some reason—you hit cancel_order to halt a live delivery immediately.

While it's en route, you keep tabs on everything. You can get real-time GPS coordinates of the assigned Shansong rider using query_rider_position. For any existing order ID, running query_order_info gives your agent the current status and all the live details about that package. If the rider needs extra motivation to pick up an order faster, you can add a monetary tip directly with add_tip.

If something goes wrong—maybe the service is bad or the delivery was botched—you submit an official complaint against the assigned rider using submit_complaint.

This setup gives your agent total control over the entire logistics lifecycle. You initiate the process by establishing the order, monitor it minute-by-minute with live tracking and status checks, and you can intervene immediately whether that means canceling a job, confirming pickup, or making sure the driver gets the incentive they need.

Built · Hosted · Managed by Vinkius Shansong Delivery MCP Server - Track & Dispatch Logistics

Server ID 019d847e-e966-735b-a803-d81278f6d28c

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is, you get a direct API bridge into Shansong's operational systems, letting your AI client handle logistics tasks without needing human intervention on external websites.

First, sign up on the Shansong Open Platform and register your application. Get your Client ID, App Secret, and Shop ID.

Push these three variables into Vurb. The node extension generates the required 'Sign' string by converting your JSON payload to an MD5 Hash for their network.

Your AI agent can now use the tools—like create_order or query_rider_position—to interact with the live delivery system.

Who is this actually for?

This server is for the operations engineer who gets tired of clicking through multiple dashboards just to answer 'Where is my package?' It’s built for teams that need real-time, automated control over physical movement and dispatch logistics.

Dispatch Coordinator

Uses calculate_fee before sending out new orders and uses create_order to formally initiate the trip.

Customer Support Agent

Runs query_rider_position instantly within a chat context to give customers live GPS updates on their package.

Retail Operations Manager

Uses cancel_order or submit_complaint autonomously when a delivery goes wrong, logging the incident immediately.

What Changes When You Connect

Real-time location updates: Stop asking agents to manually check tracking sites. Using query_rider_position lets your agent stream the rider's exact coordinates directly into a chat response.

Automated cost verification: Never guess shipping rates again. Before committing to an order, run calculate_fee to get the definitive price structure for the route.

Full lifecycle control: Need to stop or change an order? Your agent handles it with cancel_order, submitting the payload instantly and keeping your workflow clean.

Instant dispatching: From estimating costs to submitting the final request, you can execute a complete logistics flow—calculate_fee followed by create_order—in one sequence.

Proactive support handling: Instead of waiting for customers to ask 'Where is it?', your agent can proactively call query_order_info and report status updates automatically.

See it in action

01 01

Handling a delayed shipment query

A customer texts, 'What's wrong with order SS991024?' The agent immediately calls query_order_info to confirm the status. Then, it uses query_rider_position to give the customer live GPS data, confirming exactly where the rider is right now.

02 02

Setting up a new drop-off point

A coordinator needs to ship documents from Store A to Store B. The agent first calls query_store_list for both locations, then uses calculate_fee with the coordinates to confirm the price before finally calling create_order.

03 03

Correcting a misassigned rider

The initial driver is struggling. The agent first calls submit_complaint against the assigned rider for poor performance, then uses cancel_order to pull the job, allowing dispatchers to reassign it immediately.

04 04

Completing a tricky pickup

Goods were dropped off but the system hasn't logged them. The agent first calls confirm_goods and then uses add_tip on the successful delivery record to thank the rider for their help.

The honest tradeoffs

Trying to manage status updates

Anti-pattern

Writing a series of steps like: '1. Go to Order Dashboard. 2. Click Status tab. 3. Manually input the new time.' This requires jumping between multiple external web pages and copy-pasting data.

The Fix

Let your agent handle it end-to-end. Just call query_order_info with the ID, and the system returns all the status changes automatically. No dashboards needed.

Forgetting to check pricing first

Anti-pattern

Calling create_order without verifying the fee structure. You risk dispatching a job at the wrong cost or missing local surcharges.

The Fix

Always call calculate_fee first. Use that result as validation before you submit the final payload via create_order. It's a necessary two-step check.

Using generic location data

Anti-pattern

Telling customers 'The rider is near downtown.' This vague statement doesn't help solve their problem and sounds unprofessional.

The Fix

Use query_rider_position to get live coordinates. Your agent can then format this precise data (Lat/Long) into a clean, authoritative customer message.

When It Fits, When It Doesn't

Use this MCP Server if your core business process revolves around managing physical movement: dispatching goods, tracking location in real-time, or handling last-mile logistics. It’s essential when you need to execute complex chains of actions—like checking fees, creating the order, and then querying status—all without human clicks.

Don't use this if your problem is purely informational (e.g., 'What are today's weather forecasts?') or requires accessing internal HR databases. For those cases, you need a different data source type. If you only need to read static lists of cities, query_city_list works, but for actual dispatching and tracking, this is your go-to tool.

Questions you might have

How do I get live tracking using query_rider_position? +

You pass an order ID to query_rider_position. This tool returns the real-time GPS coordinates (Latitude and Longitude) of the assigned driver, allowing your agent to provide precise updates.

Do I need to calculate fees before creating an order using calculate_fee? +

Yes. Always run calculate_fee first. This confirms the current rates and total cost for the route. It’s best practice to validate pricing before you call create_order.

What if I need to cancel a delivery, what tool do I use? +

Use cancel_order. This tool sends the cancellation payload to Shansong's system. It handles stopping the dispatch and updating the status internally.

How do I submit a complaint against a driver? +

Call the submit_complaint tool directly. You provide necessary details, and the server submits an official record of the issue to Shansong's system for review.

How do I authenticate my agent to use the `create_order` tool? +

You must provide your Client ID, App Secret, and Shop ID. The Node extension handles authentication by generating a required MD5 Hash signature. This ensures that every dispatch request sent through your AI client is properly authenticated with Shansong's network.

Before calling any dispatch tool, how can I check available cities using `query_city_list`? +

The tool returns a list of all active operating cities. Running this first step confirms that your agent targets a valid geographic area. This prevents errors when calculating fees or attempting to create an order in an unsupported region.

If I need a detailed status update on an existing shipment, how does `query_order_info` work? +

This tool provides comprehensive details about the entire order lifecycle. It returns current statuses beyond just location, including key milestones like 'picked up' or 'out for delivery'. You get a full view of where the order stands.

What process does `confirm_goods` handle after a successful pick-up? +

This action formally registers that the goods were successfully picked up at the source location. It completes the first critical leg of the journey, telling Shansong's system to move the order into the official dispatch queue for routing.

How is the Shansong API payload encrypted? +

Instead of demanding complex LLM scripting to assemble clientId, JSON stringification, and MD5 encoding, this plugin seamlessly abstracts the sign variable creation. All HTTP form-data bounds are strictly governed locally on the proxy instance yielding instant results.

Connect to your AI in seconds.

Add tip

Calculate fee

Cancel order

Shansong Swift Delivery: 10 Tools for Logistics

Make your AI actually useful.

Add Tip

Calculate Fee

Cancel Order

Confirm Goods

Create Order

Query City List

Query Order Info

Query Rider Position

Query Store List

Submit Complaint

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Customer support usually means endless clicks and confusing status pages.

The Shansong Swift Delivery MCP Server: Full control over dispatching.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Handling a delayed shipment query

Setting up a new drop-off point

Correcting a misassigned rider

Completing a tricky pickup

The honest tradeoffs

Trying to manage status updates

Forgetting to check pricing first

Using generic location data

When It Fits, When It Doesn't

Questions you might have