Skip to content
Custom Connectors

Connect Proprietary ERP to Claude Code

Let Claude read across modules and update records inside your Proprietary ERP. From the terminal, inside the sessions where you already work.

How do you connect Proprietary ERP to Claude Code?

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

claude mcp add --transport http proprietary-erp 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 Proprietary ERP once connected?

Full read-write access lets Claude pull live records across modules and act inside them: update an order, adjust an inventory count, create a purchase order, or change a record's status. The cross-module lookups and data entry that used to mean switching screens and re-keying happen where the work already lives.

  • Update the status or fields on an existing order or work order
  • Adjust an inventory count or stock-location record
  • Create a purchase order or requisition from a draft you approve
  • Look up a record across modules and propose the next action
  • Append a note or update fields on a customer or vendor record
  • Flag records that fall outside a threshold for your review

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

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.