Skip to content
Custom Connectors

Connect SAP to Claude Code

Have Claude create purchase orders and post entries in SAP. From the terminal, inside the sessions where you already work.

How do you connect SAP to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect SAP, you add a SAP MCP server: a small hosted service that exposes SAP'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 SAP account. No API keys pasted into config files.

claude mcp add --transport http sap 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 SAP once connected?

Full read-write SAP access lets Claude create a purchase order, update a sales order, post a journal entry, release a blocked invoice, or check stock and propose a goods movement, then commit once you approve. The lookups and data entry that used to mean switching between transaction codes happen in one place, with an approval step before anything posts.

  • Create or update a purchase order against the right vendor and cost center
  • Create or change a sales order and confirm pricing and delivery dates
  • Post a journal entry to the correct accounts after you review it
  • Release a blocked invoice or purchase requisition once approved
  • Look up stock levels and propose a goods movement or transfer posting
  • Update master data fields on a customer, vendor, or material record

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 SAP 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 SAP API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when SAP 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 SAP 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 SAP 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 SAP 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 SAP'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 SAP?
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 SAP account it signs in with. Revoking access is one click in SAP.

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.