Connect Claude Code to your fenbs board

One command in the terminal, one sign-in in the browser, and Claude Code can file bugs from failing tests, move tasks it finishes, and read your AI context before it starts.

Last checked

Connect in one command

In your terminal
claude mcp add --transport http fenbs https://fenbs.ai/api/mcp
  1. Run the command above once, in any project.
  2. Inside Claude Code, run /mcp and choose fenbs. A browser opens on fenbs; sign in, tick what it may do, press Approve.
  3. Ask: “Run fenbs_whoami.” It answers who it is acting as and its role on your board.

For a machine that cannot open a browser — a server, a CI job — issue a token by hand under Settings, “Connect an AI assistant”, and pass it as a header. It is shown once and cannot be read back.

With a token instead of a sign-in
claude mcp add --transport http fenbs https://fenbs.ai/api/mcp --header "Authorization: Bearer YOUR_TOKEN"

What it can do once connected

  • Read the board: fenbs_list_items with filters by lane, kind or free text, and fenbs_get_item for one task with its comments.
  • Add tasks with fenbs_create_item — a Feature, an Enhancement or a Bug, in a lane, with a priority.
  • Move and edit with fenbs_update_item: change the lane, the title, the note, the kind or the priority.
  • Comment with fenbs_comment, and search across everything it can see with fenbs_search.
  • Read your AI context with fenbs_get_context — the notes you keep on the board about how you work — and add to it with fenbs_add_context_note.
  • Ask fenbs_whoami first: it answers who the assistant is acting as and what it may do, which is the question to settle before it writes anything.

What it cannot do

Anything you cannot. The assistant acts as you and holds your role on the board, narrowed by the scopes you ticked when you approved it: read, write, comment. If your role cannot move tasks between lanes, neither can the assistant, and it is told so in a sentence it can repeat to you: “You are a Viewer on Kitchen Refit, which cannot move tasks between lanes.” Revoke its token in Settings and it stops at once; everything it did stays in the history under its name.

What it is like to work with

The useful habit is to make the board the place Claude Code reports to. Tell it at the start of a session to read your AI context and the In Progress lane; tell it at the end to comment on the tasks it touched and move what it finished. Because the board records its name, you can review a day’s work in the history without reading a transcript. A CLAUDE.md line such as “Before starting, call fenbs_get_context and list In Progress items” makes it automatic.

Questions people ask.

Can Claude Code create tasks from failing tests?

Yes, if its scopes include write. Ask it to run the tests and file each failure as a Bug in To Do with the test name in the title and the error in the note. Each one gets a reference such as BU-031 that you can put in the fixing commit.

Is the assistant’s access separate from mine?

It is a separate token, listed by name under Settings, and revoking it does not touch your own sign-in. But it acts as you: it inherits your role on the board, narrowed by the scopes you ticked. It can never do something you could not.

Can I see what the assistant changed?

Yes. Every change it makes is recorded in the board’s history with its name, for example “Claude via Sam Ade”, so its work can always be told apart from a person’s.

Does connecting an assistant cost extra?

No. AI assistants are free on every plan, including the free personal board, and you can connect as many as you like.

Start with one thing.

Your own board is free. AI assistants cost nothing extra on any plan.