How to use Briefboard with Claude Code (MCP)
Connect Claude Code to Briefboard over MCP so your AI agent works straight from your real milestones, tasks, and specs.
Briefboard ships with an MCP server, which means tools like Claude Code can read and write your project directly — no copy-pasting tasks into a prompt. The agent works from the same milestones, specs, and tasks your team does.
Here's how to get set up.
What MCP gives you
MCP (the Model Context Protocol) is a standard way for AI tools to talk to external systems. Briefboard exposes its project data through an MCP server, so a connected agent can:
- Pull the next priority task assigned to it.
- Read a task's full context and acceptance criteria.
- Fetch the milestone and its specs.
- Update task status and post progress comments.
The result is an agent that always works from current, real project state instead of a stale snapshot.
Connect Claude Code
Add Briefboard as an MCP server in your Claude Code configuration. The server is registered as an HTTP streaming endpoint, so you point Claude Code at your Briefboard MCP URL and authenticate.
During local development, connect over
http://rather thanhttps://— some MCP clients use Node's certificate store and will reject a self-signed certificate otherwise.
Once connected, the Briefboard tools become available to the agent automatically.
A typical workflow
With the connection in place, the loop is straightforward:
- Ask the agent to get the next task.
- Have it pull the task prompt — it comes pre-filled with milestone and project context.
- Let it implement, checking its work against the acceptance criteria.
- Ask it to log progress in the technical channel and mark the task done.
Because every step reads and writes real Briefboard data, your board stays accurate without anyone updating it by hand.
Keep the human in the loop
The agent can move tasks and leave comments, but the important decisions — what to build, when something is truly done, when to merge — stay with you. Briefboard's job is to keep the shared picture honest while the agent does the heavy lifting.
That's the whole idea behind AI-driven development on Briefboard: give the agent real context, let it work, and keep humans focused on the outcomes.