Skip to content
Custom Connectors
SolutionsConnectorsPricingResourcesBlog
Build my connector

Connect Close to Claude Code

Make Claude create leads, log activities, and move opportunities in Close. From the terminal, inside the sessions where you already work.

Build my connectorTalk to us

How do you connect Close to Claude Code?

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

claude mcp add --transport http close 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 Close once connected?

Full read-write Close access lets Claude create a lead with its contacts, add an opportunity in the right pipeline and status, log calls, emails, and notes, update custom fields, and assign owners, all from the same conversation where you discuss the work. The CRM upkeep that used to mean switching tabs happens inline.

  • Create a new lead with its contacts and link it to the right pipeline
  • Add an opportunity with its value, confidence, and status
  • Log a call, email, or note as an activity on a lead
  • Update an opportunity's status or move it forward after you confirm
  • Set or change custom fields and the owner on a lead or contact
  • Find every lead matching a smart view query and propose follow-up tasks

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

More on the Close connector

Close connector for claude.aiSalesforce + Claude CodeHubSpot + Claude CodePipedrive + 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 connectorTalk to us