Skip to content
Custom Connectors

Connect HubSpot to Claude Code

Make Claude advance deals and log activity in HubSpot. From the terminal, inside the sessions where you already work.

How do you connect HubSpot to Claude Code?

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

claude mcp add --transport http hubspot 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 HubSpot once connected?

Full read-write HubSpot access lets Claude create and update contacts and companies, advance a deal's stage, log calls and notes against the right record, and assign or update tickets once you approve. The CRM hygiene and pipeline updates that used to mean manual data entry happen where the work already lives.

  • Create or update a contact or company record with new details
  • Advance a deal to the next pipeline stage and update its amount
  • Log a call, email, or note against the right contact or deal
  • Create a follow-up task and assign it to an owner
  • Open, update, or route a support ticket
  • Find every deal matching a query and propose batched updates

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

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.