MCP Server

Connect AI assistants like Claude Code and Claude Desktop to TaskView via the Model Context Protocol (MCP). Manage projects and tasks with a scoped API token.

TaskView ships an MCP (Model Context Protocol) server that lets AI assistants such as Claude Code and Claude Desktop work with your projects and tasks through the TaskView API.

AI client  ──stdio──▶  taskview-mcp  ──HTTPS──▶  TaskView API

Prerequisites

Node.js >= 24
A TaskView API token (tvk_...) — create one in your account settings. See API tokens.

Configuration

No installation is required — the server runs via npx. Add it to your MCP client config:

{
  "mcpServers": {
    "taskview": {
      "command": "npx",
      "args": ["-y", "taskview-mcp"],
      "env": {
        "TASKVIEW_URL": "https://api.taskview.tech",
        "TASKVIEW_TOKEN": "tvk_your_token_here"
      }
    }
  }
}

Claude Code — add to .claude/settings.json (project) or ~/.claude.json (global).
Claude Desktop — add to claude_desktop_config.json.

Set TASKVIEW_URL to your own instance when self-hosting.

The assistant can only do what the API token allows. Token permissions are scoped to selected projects and intersected with your RBAC role, so an AI client never exceeds your own access. Grant the minimum scope needed.

GitHub & GitLab Setup

Connect GitHub and GitLab repositories to TaskView. Import and sync issues as tasks with OAuth authorization, webhook-based real-time updates, and AES-256 encrypted token storage. Supports GitHub Enterprise and self-hosted GitLab.

Environment Variables

Complete reference for TaskView environment variables - database connection, JWT authentication, OAuth providers, SMTP email, GitHub/GitLab integration, encryption, and CORS configuration for your self-hosted Docker deployment.

MCP Server

Prerequisites

Configuration

Permissions