Skip to content
Custom Connectors

Connect Confluence to Claude Code

Make Claude draft and update pages directly in Confluence. From the terminal, inside the sessions where you already work.

How do you connect Confluence to Claude Code?

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

claude mcp add --transport http confluence 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 Confluence once connected?

Full read-write Confluence access lets Claude create new pages from your notes, update existing documentation in place, move pages between spaces, manage labels, and post comments once you approve. The drafting and upkeep that used to mean copy-paste happen inside the space where your knowledge already lives.

  • Create a new page from meeting notes and file it under the right space
  • Update an existing page in place, preserving its history and version trail
  • Add or remove labels to keep a space organized and searchable
  • Post a comment or inline reply on a page after you approve it
  • Move or restructure pages between spaces as a project evolves
  • Draft a templated page, such as a retro or runbook, 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 Confluence 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 Confluence API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Confluence 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 Confluence 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 Confluence 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 Confluence 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 Confluence'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 Confluence?
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 Confluence account it signs in with. Revoking access is one click in Confluence.

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.