Skip to content
Custom Connectors
SolutionsConnectorsPricingResourcesBlog
Build my connector

Connect Fivetran to Claude Code

Let Claude trigger syncs and manage connectors in Fivetran. From the terminal, inside the sessions where you already work.

Build my connectorTalk to us

How do you connect Fivetran to Claude Code?

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

claude mcp add --transport http fivetran 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 Fivetran once connected?

Full read-write Fivetran access lets Claude trigger or pause syncs, pause and resume connectors, adjust schema and table sync settings, run dbt transformations, and update sync frequency against an account you control. The connector tuning and sync babysitting that used to mean clicking through the dashboard happens in conversation, with every change reviewed before it runs.

  • Trigger a sync on a named connector and report when it completes
  • Pause or resume a connector after you confirm the action
  • Enable or disable specific schemas, tables, or columns from a sync
  • Adjust a connector's sync frequency to a new interval
  • Run a dbt transformation or scheduled transformation job on approval
  • Inspect connector status and recent sync history to diagnose a failure

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

More on the Fivetran connector

Fivetran connector for claude.aiAmazon Redshift + Claude CodeLooker + Claude CodeMetabase + 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