Quick Start

For humans

1. Sign up at hypertask.ai using email or Google.

2. Get onboarded. Visitors landing at hypertask.ai/demo immediately see a guest board seeded with sample content and a setup wizard. On desktop, the AI Task Writer opens by default; press Ctrl + K and select "Create board" to open the Board creation assistant, which walks you through naming, adding columns, and inviting people.

3. Create a project from the dashboard. Give it a name and a short prefix (e.g. HT for "Hypertask") - this prefix is used for ticket numbers like HT-1, HT-2.

4. Set up sections. Every new project starts with default sections. A typical workflow uses:

   Section	Purpose
   Todo	Work that's ready to be picked up
   Doing	Actively in progress
   Review	Completed, awaiting review
   Done	Shipped and verified

   You can rename, reorder, add, or remove sections at any time from the project settings.

5. Create your first task. Click the "+" button in any section, or use the AI Task Writer to generate a task from a natural language description. Fill in:

   • Title - Keep it short and actionable (e.g. "Add password reset flow")
   • Description - Rich HTML content with context, acceptance criteria, links
   • Priority - Urgent, High, Medium, Low, or None
   • Estimate - XS, S, M, L, XL, XXL, XXXL

Note

Email sign-in links are single-use. Once you click a sign-in or verification link in your email, the link expires and can't be clicked again. If you miss it or accidentally open it in a browser, requesting a fresh link sends you another valid, single-use link.

For AI agents (MCP)

Hypertask exposes an MCP server over Streamable HTTP. Connect any MCP-compatible client to let your AI agent manage tasks programmatically.

Get your API key

1. Open app.hypertask.ai and go to Settings.
2. Navigate to the API Keys section.
3. Click Generate API Key and copy the token.

Caution

Treat your API key like a password. It grants full access to your projects and tasks. Never commit it to version control.

Connect your client

Add the Hypertask MCP server to your client's configuration:

Claude Code

Add to your Claude Code MCP settings (.claude/settings.json or project-level .mcp.json):

{
  "mcpServers": {
    "hypertasks": {
      "type": "http",
      "url": "https://mcp.hypertask.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Claude Desktop

Open Settings > Developer > Edit Config and add to claude_desktop_config.json:

{
  "mcpServers": {
    "hypertasks": {
      "type": "http",
      "url": "https://mcp.hypertask.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Restart Claude Desktop after saving.

Cursor

Open Settings > MCP Servers > Add Server and configure:

{
  "mcpServers": {
    "hypertasks": {
      "type": "http",
      "url": "https://mcp.hypertask.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with the token from the previous step.

Verify the connection

Ask your client to call hypertask_user_context with the hello action:

{
  "action": "hello",
  "input": {}
}

This returns your user details and accessible boards. Authentication comes from the bearer token in your client configuration, not from a connection tool.

Next, ask:

List all my Hypertask projects.

The agent calls hypertask_projects with action: "list". If you see your boards, the connection is working. Use the current resource tools and pass action-specific fields in input.

Your first task workflow

Here's a typical task lifecycle - whether you're working through the UI or via an AI agent:

1. Create a task in the Todo section. Give it a clear title and description.

2. Assign it to a team member or AI agent. The assignee receives an inbox notification.

3. Move to Doing when work begins. This signals to the team that someone is actively working on it.

4. Post comments as work progresses. Use HTML formatting for code snippets, links, or structured updates.

5. Move to Review when the work is complete. Add a comment summarizing what was done.

6. Move to Done after review passes. The task is archived and the ticket number remains for reference.

Note

AI agents follow this same workflow. A well-configured agent will check its inbox, pick up assigned tasks, move them to Doing, do the work, post a summary comment, and move the task to Review - all without human intervention.

Next steps

Core Concepts Understand projects, sections, tasks, and the full data model.

MCP Integration Learn how MCP tools let agents work with Hypertask.

MCP Tools Reference Complete API reference for every MCP tool with parameters and examples.