Connecting the MCP server
What is an MCP server
Section titled “What is an MCP server”MCP (Model Context Protocol) is an open standard that lets an AI call the tools of external services directly. By connecting UTasks as an MCP server, you give your AI agent the ability to manage your tasks in real time, instead of retelling them by hand.
Once the MCP server is connected, a number of practical scenarios become possible:
The AI agent can show you all tasks assigned to you and filter them by project, status, priority or date range – for example, “show me tasks for the next 7 days” or “what’s overdue”. It can create new tasks and assign them right away, comment on tasks, mark them as completed or reopen them, and pull up the list of members and projects, so you don’t have to look up names and IDs by hand.
This is handy when UTasks is your main work tool: instead of switching between Telegram and your AI chat, you can keep the whole conversation about tasks in one place, and the AI agent fetches up-to-date data from UTasks on its own.
How to connect (using Claude as an example)
Section titled “How to connect (using Claude as an example)”Open your profile in the AI and go to Settings.
old screenshotThen Connectors → Add → Add custom connector.
old screenshotIn the connector settings window, enter a name for the server (whatever is convenient for you) and the address https://app.utasks.io/utb/mcp. Click Add.
old screenshotIn the next window, the AI agent will ask for an API key to connect to UTasks.
Open UTasks and send the command /apikey new. Copy the key.

Enter the copied key to connect. Click “Allow”.
old screenshotHow to use it
Section titled “How to use it”Once connected, you can give the AI agent commands like: “show me my tasks for today”, “what tasks are overdue”, “create a task and assign it to Viktor”, “mark the task as completed”.
old screenshotDepending on what your AI can do, you can, for example, set up a regular morning summary of planned tasks or an evening summary of completed ones.
Good luck!