Boxzooka MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Boxzooka MCP Servershow me the current inventory for SKU 1001"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Boxzooka MCP Server
Wraps the Boxzooka bxz-api (Product, Inbound, Order, Inventory, Shipment, Return) as an MCP server, same pattern as the Materials Inventory connector: one shared server, one shared credential pair, the whole team connects to the same URL.
33 tools, full read + write coverage. EDI is not covered — it's XML-based and Boxzooka requires a separate setup conversation with their IT team for it; ask if you actually need it and I'll add it.
Files
boxzooka_mcp.py— the serverrequirements.txt— Python depsDockerfile— container build for remote hosting
Related MCP server: MoySklad MCP Server
1. Deploy it (separate service from Materials Inventory)
This is a separate deployment from the Materials Inventory connector — each server needs its own Railway/Render/Fly service.
Push these three files to a new repo (or folder in an existing one).
Railway → New Project → Deploy from GitHub repo → pick it.
In Variables, add:
BOXZOOKA_API_TOKEN= your sandbox token (c44f966f5c7fc4cdb7d7f461ab4414c6)BOXZOOKA_CUSTOMER_ID=242Optional:
BOXZOOKA_API_BASE_URL— only needed once Boxzooka gives you a live/production URL to replace the sandbox (https://sandbox.boxzooka.com, the default).
Railway gives you a public URL, e.g.
https://boxzooka-production-xxxx.up.railway.app.The connector URL to give your team is that URL plus
/mcp:https://boxzooka-production-xxxx.up.railway.app/mcp
2. Connect the team
Same as Materials Inventory: each teammate adds it as a custom connector in their own Claude app, pointing at the URL above. No per-user setup.
3. Security & sandbox notes
This token/customer pair currently points at Boxzooka's sandbox environment (per their docs: "for test and debug purpose"). Data you see through it is test data, not your real warehouse — orders and inventory here won't reflect what's actually happening at Boxzooka's physical warehouse. Once you're ready to go live, contact Boxzooka for production credentials and set them via
BOXZOOKA_API_TOKEN/BOXZOOKA_CUSTOMER_ID/BOXZOOKA_API_BASE_URL.Same access-level note as Materials Inventory: this connector can create orders, cancel orders, adjust returns, etc. — full read/write. Don't share the URL outside the team.
4. What's covered
Product: create, get by SKU, update, list all, list (paginated)
Inbound: create, get by PO number, search by date range, get received-by-date (real-time), update, paginated receiving-by-date
Order: create, cancel, search (by order_id/order_key/external_id), update, load WMS orders by date
Inventory: list all in-stock, get by SKU, today's adjustments, adjustments by date, putaway by date, plus paginated variants of each
Shipment: get by order key, get by date range, paginated by-date
Return: search, search by date, create, update, cancel
Not covered: EDI (XML-based, needs a separate Boxzooka IT conversation).
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TomDimond/Boxzooka'
If you have feedback or need assistance with the MCP directory API, please join our Discord server