Connect Katana to Claude Code

Have Claude create orders and update stock in Katana. From the terminal, inside the sessions where you already work.

How do you connect Katana to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Katana, you add a Katana MCP server: a small hosted service that exposes Katana's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Katana account. No API keys pasted into config files.

claude mcp add --transport http katana https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Katana once connected?

Full read-write Katana access lets Claude create and update the records you work in: draft a sales order from an email, create a manufacturing order for a product, raise a purchase order against the right supplier, or update a product or material, then route it for your approval. The data entry that used to mean clicking through the web app happens where the records already live.

Draft a sales order from an email or quote you paste in
Create a manufacturing order for a product and its quantity
Raise a purchase order against the right supplier and materials
Create or update product, material, and customer records
Update stock details, pricing, or supplier fields on a record
Search orders matching a filter and propose batched field edits

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Katana access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Katana API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Katana changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Katana connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Katana connector work in claude.ai and Claude Code?

Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Katana account, so access always matches what that person can already see and do.

Do I need to host or maintain anything myself?

No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Katana's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.

Is it safe to give a coding agent write access to Katana?

Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Katana account it signs in with. Revoking access is one click in Katana.

More on the Katana connector

Katana connector for claude.ai Dynamics 365 Business Central + Claude Code Acumatica + Claude Code Epicor + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connector Talk to us