Connect Claude Code to Agenticboard

Claude Code is Anthropic's agent in your terminal, and Agenticboard is the project board it can actually work. Agenticboard runs an MCP server, so once you add it Claude Code reads the same board, tickets and docs your team uses — and writes back to them. One command, one scoped token, no plugin to install.

Endpoint

https://agenticboard.app/api/mcp/

Transport

Streamable HTTP, JSON-RPC 2.0

Auth

Bearer token, agb_…

Set it up

1. 1

   Create a scoped token

   In Agenticboard, open Settings → API tokens → New token and choose three things: the access level, either Read only for viewing boards, tasks and docs or Read & edit to also create and update tasks, comment, edit docs and attach files; which projects it may touch, all of them or an allow-list; and whether it can read and write documentation. Copy the token when it is shown — it is only displayed once.

2. 2

   Add the server to Claude Code

   Run this in your terminal, with your own token in place of the placeholder.

   claude mcp add --transport http agenticboard \
     https://agenticboard.app/api/mcp/ \
     --header "Authorization: Bearer agb_your_token_here"

3. 3

   Check that it answers

   Ask Claude Code to list your projects, or call tools/list. You should see the tools your token is allowed to use: the write tools appear only for a Read & edit token, and the doc tools only when documentation access is on.

What your agent can do

The token decides the shape of the toolset. These are the tools the MCP server exposes.

• Read the board.list_projects, get_board, get_task and list_members give it columns, cards, labels, comments, attachments and testing feedback.
• Move the work along.create_task and update_task open a card or change its title, description, status, priority, type, assignee, deadline, PR URL, version or cycle.
• Follow your process.get_workflow returns the project's ordered steps, and the write tools return the next step to take, so the agent works reproduce, fix, test, document in the order you set.
• Check what is already solved.find_resolved searches done tasks and returns how each was fixed, and get_task_history gives one ticket's full trail.
• Read and keep the docs.list_docs, get_doc, create_doc and update_doc work the same pages your team reads. Edits carry a reason into the doc's version history.
• Leave the evidence behind.comment_task, add_test_report and attach_file put the test result and the screenshot on the card, where a reviewer will look for them.
• Find anything.search covers projects, tasks and docs, and get_history with search_history reach the knowledge behind them: doc changes, resolved tickets and captured errors.

A token acts as you, narrowed by its scope, and every call it makes is logged under the token's Activity. Revoke it any time from Settings → API tokens; anything using it loses access immediately.

Other guides: Cursor · Claude Desktop · claude.ai · Sentry