machship-mcp
Integrates the Machship freight management platform with MCP-compatible LLMs, enabling shipment creation, quotes, labels, and carrier management via natural language.
README
Machship MCP Server
A Model Context Protocol server that integrates AI assistants with the Machship freight management platform. Built on a production-ready TypeScript foundation, it provides comprehensive access to Machship for consignment management, quoting, labelling, manifesting, and more — through any MCP-compatible AI client.
Built by Devkind — cutting-edge software development serving businesses globally.
Features
- Full Machship API Coverage: ~65 tools across 21 modules — consignments, quotes, labels, manifests, carriers, locations, and more
- Dual Transport Support: STDIO and HTTP transports for AI assistant and web integration
- Type Safety: Full TypeScript implementation with Zod schema validation
- npx Ready: Zero-install usage via
npx machship-mcp - Docker Support: Production Docker image on Docker Hub
- Any MCP Client: Works with Claude Desktop, Cursor, VS Code, Windsurf, and more
Available Tools
| Module | Tools |
|---|---|
| Authenticate | ping |
| Attachments | get, POD report, batch download, upload |
| CarrierInvoices | list, entries, reprice, auto-reconcile |
| CommercialInvoices | upload |
| Companies | list, carriers/accounts/services |
| CompanyItems | get, list, by-sku, complex variants, create, delete |
| CompanyLocations | get, list, create, edit, permanent pickups |
| Consignments | get, batch, by-reference, create, edit, delete, search, statuses |
| Consolidation | group, perform, group+perform |
| CustomSchemas | get all, get by id, create, update, delete |
| FinancialInvoice | list posted, get by document number |
| Labels | consignment PDF, item PDF, manifest PDF, batch zip, print, dangerous goods |
| Locations | search, exact match, with options |
| Manifests | list, group, manifest/book, rebook pickup |
| Notes | get consignment notes |
| OrganisationLinks | get links, add, remove, public key management |
| PendingConsignments | create, get, batch, by-reference, recent, delete |
| Quotes | create, create with complex items, list, get |
| Routes | get routes, batch routes, complex items routes |
Total: ~65 tools
Quick Start (No Install Required)
No cloning, no global installs — just Node.js 18+ and a Machship API token.
Step 1 — Get your Machship API token
- Log into your Machship account
- Go to Settings → API
- Generate a Bearer token — this is your
MACHSHIP_API_TOKEN
Step 2 — Add to your MCP client (pick one below)
Step 3 — Restart your client and start chatting
To verify it works, ask: "Ping the Machship API" — you should get a successful response.
Client Setup
Claude Desktop
Edit ~/.claude/claude_desktop_config.json (create it if it doesn't exist):
{
"mcpServers": {
"machship": {
"command": "npx",
"args": ["-y", "machship-mcp"],
"env": {
"MACHSHIP_API_TOKEN": "your-token-here"
}
}
}
}
Restart Claude Desktop — the Machship tools will appear automatically.
Claude Code (CLI)
Run once to add to your project MCP config:
claude mcp add machship -- npx -y machship-mcp
Then set the token in your environment or .env:
export MACHSHIP_API_TOKEN=your-token-here
Or add it directly to .mcp.json after running the command above:
{
"mcpServers": {
"machship": {
"command": "npx",
"args": ["-y", "machship-mcp"],
"env": {
"MACHSHIP_API_TOKEN": "your-token-here"
}
}
}
}
<details> <summary>Cursor</summary>
One-click install:
<img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Install in Cursor">
Manual setup:
Go to Cursor Settings → MCP → Add new MCP Server:
- Name: Machship MCP
- Type: command
- Command:
npx -y machship-mcp - Environment variable:
MACHSHIP_API_TOKEN=your-token-here
</details>
<details> <summary>VS Code</summary>
Install via the VS Code CLI (one command):
code --add-mcp '{"name":"machship","command":"npx","args":["-y","machship-mcp"],"env":{"MACHSHIP_API_TOKEN":"your-token-here"}}'
Or follow the MCP setup guide and use this config:
{
"mcpServers": {
"machship": {
"command": "npx",
"args": ["-y", "machship-mcp"],
"env": {
"MACHSHIP_API_TOKEN": "your-token-here"
}
}
}
}
</details>
<details> <summary>Windsurf</summary>
Follow the Windsurf MCP documentation and add to your MCP configuration file:
{
"mcpServers": {
"machship": {
"command": "npx",
"args": ["-y", "machship-mcp"],
"env": {
"MACHSHIP_API_TOKEN": "your-token-here"
}
}
}
}
</details>
<details> <summary>Goose</summary>
Go to Advanced settings → Extensions → Add custom extension:
- Name: Machship MCP
- Type: STDIO
- Command:
npx -y machship-mcp - Environment variable:
MACHSHIP_API_TOKEN=your-token-here
</details>
<details> <summary>LM Studio</summary>
Go to Program in the right sidebar → Install → Edit mcp.json and add:
{
"mcpServers": {
"machship": {
"command": "npx",
"args": ["-y", "machship-mcp"],
"env": {
"MACHSHIP_API_TOKEN": "your-token-here"
}
}
}
}
</details>
<details> <summary>Warp</summary>
Go to Settings → AI → Manage MCP Servers → + Add, or use the slash command /add-mcp in the Warp prompt:
{
"mcpServers": {
"machship": {
"command": "npx",
"args": ["-y", "machship-mcp"],
"env": {
"MACHSHIP_API_TOKEN": "your-token-here"
}
}
}
}
</details>
Run directly (test / CLI use)
# STDIO mode — pipe JSON-RPC directly
MACHSHIP_API_TOKEN=your-token npx -y machship-mcp
# HTTP mode — exposes a local MCP endpoint
MACHSHIP_API_TOKEN=your-token TRANSPORT=http npx -y machship-mcp
# MCP endpoint: http://localhost:3000/mcp
# Health check: http://localhost:3000/health
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
MACHSHIP_API_TOKEN |
Yes | — | Machship Bearer token |
MACHSHIP_API_URL |
No | https://live.machship.com |
Override API base URL |
TRANSPORT |
No | stdio |
stdio or http |
PORT |
No | 3000 |
HTTP port (when TRANSPORT=http) |
Example Interactions
Once connected, ask your AI assistant:
"Search for freight routes from Melbourne 3000 to Sydney 2000 for a 10kg parcel"
"Create a consignment for company 123 shipping to Brisbane"
"Get all unmanifested consignments for company 456"
"What carriers and services are available for company 789?"
"Get the label PDF for consignment 12345"
"Show me completed consignments from last week"
"Create a quote with complex items for express delivery"
Transport Modes
| Mode | When to use |
|---|---|
stdio (default) |
AI desktop clients (Claude Desktop, Cursor, VS Code, etc.) — JSON-RPC over stdin/stdout |
http |
Web integrations, remote servers, or anything that needs an HTTP MCP endpoint |
Set the mode via the TRANSPORT environment variable (see Environment Variables below).
Docker
Pull and run from Docker Hub — no Node.js required:
docker run -e MACHSHIP_API_TOKEN=your-token \
-e TRANSPORT=http \
-p 3000:3000 \
devkind/machship-mcp:latest
For stdio mode in MCP clients:
{
"mcpServers": {
"machship": {
"command": "docker",
"args": ["run", "--rm", "-i",
"-e", "MACHSHIP_API_TOKEN=your-token-here",
"devkind/machship-mcp:latest"]
}
}
}
Development
Quick Start
# Clone and install
git clone https://github.com/devkindhq/machship-mcp.git
cd machship-mcp
yarn install
# Build
yarn build
# Run in STDIO mode
MACHSHIP_API_TOKEN=your-token yarn start
# Run in HTTP mode
MACHSHIP_API_TOKEN=your-token TRANSPORT=http yarn start
# Development with watch mode
MACHSHIP_API_TOKEN=your-token yarn dev
Scripts
yarn build # Compile TypeScript to dist/
yarn dev # Watch mode with tsx
yarn start # Run compiled server
yarn clean # Remove dist/
# Docker
yarn docker:build # Build image as devkind/machship-mcp:latest
yarn docker:build:version # Tag with package version + latest
yarn docker:run # Run locally in HTTP mode on port 3000
yarn docker:push # Push latest to Docker Hub
yarn docker:push:version # Push version tag + latest to Docker Hub
yarn docker:release # Full pipeline: build + tag + push
Publishing to npm
# Login to npm
npm login
# Publish
npm publish
Publishing to Docker Hub
# Login to Docker Hub
docker login
# Build, tag, and push
yarn docker:release
License
Resources
- MCP Specification
- MCP SDK
- Machship API Documentation
- Devkind — the team behind this server
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.