Taskade MCP Server

The Workspace MCP (@taskade/mcp-server) — run your Taskade workspace from any AI client.

Connect Taskade to any AI assistant — Claude, Cursor, Windsurf, VS Code, and more — via the Model Context Protocol.

62 tools for workspaces, projects, tasks, AI agents, agent chat, webhooks, knowledge bases, templates, media, and sharing — all from your AI client.

• MCP Server — Connect Taskade to Claude Desktop, Cursor, Windsurf, or any MCP client.
• OpenAPI Codegen — Generate MCP tools from any OpenAPI spec — not just Taskade.

Contents

• Demo
• Quick Start
• Hosted remote MCP
• Tools (62)
• Why Taskade MCP?
• Agent Recipes
• Use Cases
• OpenAPI Codegen
• What is Taskade?
• Roadmap
• Contributing
• License

Demo

MCP-powered Taskade agent running inside Claude Desktop by Anthropic:

Quick Start

⚡ Prefer a hosted option? Open https://www.taskade.com/mcp in a browser — that's the official OAuth install page (Claude, Cursor, Claude Code, Windsurf, Zed). An unauthenticated initialize returns 401 by design; clients complete OAuth 2.0 (PKCE) once. Full task-level writes still live in this local Workspace MCP package. Guide: Hosted Taskade MCP.

Which Taskade MCP do I want?

Taskade speaks MCP through three surfaces — this repo is the first one:

1. Get Your API Key

Go to Taskade Settings > API and create a Personal Access Token.

2. Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "taskade": {
      "command": "npx",
      "args": ["-y", "@taskade/mcp-server"],
      "env": {
        "TASKADE_API_KEY": "your-api-key-here"
      }
    }
  }
}

3. Cursor

Add to your Cursor MCP settings:

{
  "mcpServers": {
    "taskade": {
      "command": "npx",
      "args": ["-y", "@taskade/mcp-server"],
      "env": {
        "TASKADE_API_KEY": "your-api-key-here"
      }
    }
  }
}

4. Windsurf

Add to ~/.codeium/windsurf/mcp_config.json (or Settings → Cascade → MCP → Add Server):

{
  "mcpServers": {
    "taskade": {
      "command": "npx",
      "args": ["-y", "@taskade/mcp-server"],
      "env": {
        "TASKADE_API_KEY": "your-api-key-here"
      }
    }
  }
}

5. Cline

In VS Code, open the Cline MCP Servers panel → Configure MCP Servers and add:

{
  "mcpServers": {
    "taskade": {
      "command": "npx",
      "args": ["-y", "@taskade/mcp-server"],
      "env": {
        "TASKADE_API_KEY": "your-api-key-here"
      }
    }
  }
}

6. VS Code

Add a .vscode/mcp.json to your workspace (VS Code uses the servers key; ${input:…} prompts for your key on first run):

{
  "servers": {
    "taskade": {
      "command": "npx",
      "args": ["-y", "@taskade/mcp-server"],
      "env": {
        "TASKADE_API_KEY": "${input:taskade_api_key}"
      }
    }
  }
}

7. HTTP / SSE Mode (remote & custom clients)

TASKADE_API_KEY=your-api-key npx @taskade/mcp-server --http

The server starts at http://localhost:3000 (configure with PORT env var). Connect via SSE at http://localhost:3000/sse?access_token=your-api-key.

8. Hosted remote MCP (https://www.taskade.com/mcp)

Official remote Taskade MCP. Nothing to install locally. Paste the URL into any MCP client that supports Streamable HTTP + OAuth.

{
  "mcpServers": {
    "taskade": {
      "type": "http",
      "url": "https://www.taskade.com/mcp"
    }
  }
}

Hosted tools cover workspace browse (list_spaces, inspect_space), project/agent create, and Genesis app/ file edits via write_file. Task-level writes (complete, assignees, dates) are still this package.

Tools (62)

Workspaces

Projects

Tasks

AI Agents

Create, manage, and publish autonomous AI agents with custom knowledge and tools.