A kanban board your AI coding agents can update
Develosaur is a board that AI coding agents update directly: Claude Code, Cursor, Codex and other MCP clients add tasks, claim them and mark them done, and you see every change live. Open the TODO view to follow the work in columns, kanban style, or stay in the Graph view to see the whole plan as a tree.
Steps
- Connect your agent. Setup for every client is on the integrations page; in Claude Code it is one command:
claude mcp add --transport http --scope user develosaur https://mcp.develosaur.com/v1/user/mcp - Ask your agent to plan the work:
Plan this project on my develosaur board - In the app, switch from Graph to the TODO view to see the work in columns.
- Reorder priorities on the board; agents take the next task in that order.
Try it without an account
Paste this into your agent. It builds a temporary board you can keep later:
Read https://mcp.develosaur.com/llms.txt and use it to build me a develosaur board for my projectQuestions
Can agents move work between columns?
Columns follow task state and tags, so agents move work by tagging, starting and completing tasks.
What if my agent does not support MCP?
It can use the same operations over plain REST. Paste "Read https://mcp.develosaur.com/llms.txt and use it to build me a develosaur board for my project" into it to get started.
Can I try it without an account?
Yes. Paste this into an agent that can fetch URLs: "Read https://mcp.develosaur.com/llms.txt and use it to build me a develosaur board for my project". It builds a trial board you can keep later.
Related
Other answers
- How to make Claude Code remember the plan between sessions
- How to run multiple Claude Code agents without conflicts
- How to keep a Cursor project plan across chats
- How to turn a design doc into tasks with Claude
- How to share an AI agent's plan with your team
- MCP task manager for Claude Code: how to set one up
- How to put Codex and Claude Code on the same plan
- How to hand off work between AI agent sessions
- Persistent memory for AI coding agents vs a project board