gobox-mcp
Enables AI agents and automation tools to interact with the Gobox e-commerce platform, providing tools for orders, products, inventory, warehouses, reports, shipments, and webhooks.
README
gobox-mcp
MCP server wrapping the Gobox Open API (dev-api.gobox.asia/open/api/*) for AI agents, Claude Desktop, and CLI automation.
Features
- ~40 tools covering orders, products, SKU quantities, warehouses, reports, shops, locations, consignments, Goship rates, webhooks
- 5 SKU quantity states: available, in_warehouse, keep_pick, wait_qc, wait_incoming (+ composite
sku_full_status) - Dual transport: stdio (Claude Desktop local) or SSE (Docker shared for bot/team)
- Auto token refresh with in-memory cache
- Modular: each tool group in its own file under
tools/
Setup
1. Credentials
Contact Gobox admin for client_id + client_secret.
2. Install
cd gobox-mcp
python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
# Edit .env with your credentials
3. Run locally (stdio)
python gobox_mcp.py
4. Run in Docker (SSE)
docker compose up -d
# Test: curl http://localhost:8000/sse
Connect to Claude Desktop
Stdio mode (local)
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"gobox": {
"command": "/absolute/path/to/gobox-mcp/.venv/bin/python",
"args": ["/absolute/path/to/gobox-mcp/gobox_mcp.py"],
"env": {
"GOBOX_BASE_URL": "https://dev-api.gobox.asia",
"GOBOX_CLIENT_ID": "xxx",
"GOBOX_CLIENT_SECRET": "xxx"
}
}
}
}
SSE mode (Docker)
{
"mcpServers": {
"gobox": {
"url": "http://localhost:8000/sse"
}
}
}
Connect to Claude Code
claude mcp add gobox \
/absolute/path/.venv/bin/python \
/absolute/path/gobox_mcp.py \
-e GOBOX_BASE_URL=https://dev-api.gobox.asia \
-e GOBOX_CLIENT_ID=xxx \
-e GOBOX_CLIENT_SECRET=xxx
Environment switching (dev/prod)
Set GOBOX_BASE_URL to switch:
- Dev:
https://dev-api.gobox.asia - Prod:
https://api.gobox.asia(verify actual prod URL)
Tool catalog
| Module | Tools |
|---|---|
orders_tools |
list_orders, get_order, create_order, update_order, update_order_status, cancel_order, send_order_to_goship |
products_tools |
list_products, get_product, list_categories, list_brands, list_attributes, sku_quantity_available, sku_quantity_in_warehouse, sku_quantity_keep_pick, sku_quantity_wait_qc, sku_quantity_wait_incoming, sku_full_status |
warehouses_tools |
list_warehouses, list_inventories, list_warehouse_pickings |
reports_tools |
report_warehouse_import, report_warehouse_import_refund, report_export_by_order, report_export_by_sku, report_inventories, report_warehouse_store, report_warehouse_stock, report_materials |
shops_tools |
list_shops |
locations_tools |
list_cities, list_districts, list_wards, list_countries, get_sys_helpers |
consignments_tools |
list_consignments, get_consignment, create_consignment, cancel_consignment |
goship_tools |
get_shipping_rates |
webhooks_tools |
list_webhooks, create_webhook, update_webhook, delete_webhook, toggle_webhook |
Example AI queries
"List all Gobox warehouses" "Check stock for SKU ABC123" → calls
sku_full_status("ABC123")"Có bao nhiêu đơn Shopee chưa giao hôm nay?" "Báo cáo nhập kho tháng này"
Troubleshooting
OAuth fails: Verify GOBOX_GRANT_TYPE (default client_credentials). Contact admin if unsure.
FastMCP SSE DNS rebinding error: Add transport_security=TransportSecuritySettings(enable_dns_rebinding_protection=False) to mcp.run() call.
Token expired mid-call: Auto-refresh handles this. If persists, call gobox_auth.clear_cache().
Project structure
gobox-mcp/
├── gobox_mcp.py # Main entry
├── gobox_auth.py # OAuth token cache
├── gobox_client.py # HTTP helper
├── tools/
│ ├── orders_tools.py
│ ├── products_tools.py
│ ├── warehouses_tools.py
│ ├── reports_tools.py
│ ├── shops_tools.py
│ ├── locations_tools.py
│ ├── consignments_tools.py
│ ├── goship_tools.py
│ └── webhooks_tools.py
├── Dockerfile
├── docker-compose.yml
├── requirements.txt
├── .env.example
└── README.md
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.