proship-mcp
Stateless MCP server that enables AI agents to create Thailand Post shipments, print labels, and track parcels through the ProShip API.
README
proship-mcp
Stateless MCP (Model Context Protocol) server that lets any AI agent create Thailand Post shipments, print labels, and track parcels through ProShip.
- Endpoint:
POST https://mcp.proship.me/mcp(JSON-RPC 2.0, application/json) - Docs: open
https://mcp.proship.me/mcpin a browser — the docs page is generated from the live tool registry - Auth:
Authorization: Bearer <ProShip API token>, passed through verbatim toapi.proship.me. Nothing is stored server-side. New users can call the publicsignuptool to get a token.
Tools
Public: track_parcel, get_order_statuses, signup.
Authenticated: list_shops, create_order, list_orders, get_order, update_order_status, cancel_order, check_duplicate, print_label.
The browser docs page at /mcp is the canonical, always-current tool reference.
Run
npm install
npm start # listens on PORT (default 3000)
npm test # node:test suite, upstream fully mocked
Environment
| Var | Purpose | Default |
|---|---|---|
PORT |
listen port | 3000 |
PUBLIC_URL |
absolute base used in label URLs and docs | https://mcp.proship.me |
PROSHIP_API_BASE |
upstream API base | https://api.proship.me |
PROSHIP_UTRACK_TOKEN |
optional server-side token enabling unauthenticated track_parcel |
unset |
PROSHIP_SYNTH_EMAIL_DOMAIN |
domain for synthesized signup emails | proship.me |
Deploy
Fly.io app proship-mcp (region sin):
fly deploy # add --depot=false if the Depot builder fails
Notes
- Order ids are pipe-suffixed (
order-xxx|123). GET/PUT/DELETE strip the suffix internally;print_labelrequires the full id. Always pass the full id between tools. - Weights are grams. Status codes use the Thai pipeline (
get_order_statuses); code 6 means out for delivery despite upstream labeling it "ERROR". - The only server state is a 10-minute in-memory cache for label PDFs so
print_labelcan return a URL.
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.