clickup

ClickUp MCP Server - Integrate ClickUp project management with AI through Model Context Protocol

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio taazkareem-clickup-mcp-server node path/to/server.js \
  --env MCP_SERVER_HOST="0.0.0.0" \
  --env MCP_SERVER_PORT="undefined_or_port" \
  --env CLICKUP_BASE_URL="https://api.clickup.com/api" \
  --env CLICKUP_API_TOKEN="your_clickup_api_token_here"

How to use

This MCP server provides a premium integration with ClickUp, exposing a model-context-driven interface to manage ClickUp resources through natural language and AI-assisted workflows. It supports core ClickUp capabilities such as tasks, checklists, comments, tags, spaces, lists, folders, files, docs, chat, and time tracking, with advanced features like smart search, multi-tenant authentication, and flexible views. You can connect AI agents or agentic workflows to issue natural-language commands (for example, create a task with subtasks, update a due date, or post a comment) and the MCP layer will translate those intents into ClickUp API actions. The server includes hybrid authentication, OAuth 2.1-style flows, and tenant isolation to keep data separated across clients. To start using, ensure the MCP server is running and authenticate your agent or workflow to obtain a valid session, then invoke the available tools through your MCP client to perform ClickUp operations in a conversational or programmatic manner.

How to install

Prerequisites:

Node.js (LTS version recommended, e.g., 18.x) and npm installed on your system
Access token for ClickUp API with appropriate scopes

Installation steps:

Install the MCP server package from npm: npm install -g @taazkareem/clickup-mcp-server
Verify installation: clickup-mcp-server --version
Configure environment variables (examples):
- CLICKUP_API_TOKEN=your_clickup_token
- CLICKUP_BASE_URL=https://api.clickup.com/api
- MCP_SERVER_HOST=0.0.0.0
- MCP_SERVER_PORT=8080
Run the MCP server: npx @taazkareem/clickup-mcp-server or node path/to/server.js
Connect your MCP client or AI agent to the running endpoint and begin issuing ClickUp actions via natural language.

Additional notes

Tips and common issues:

Ensure your ClickUp API token has the required scopes for tasks, lists, spaces, docs, and time tracking.
If you encounter authentication failures, verify token scopes and that the MCP server can reach ClickUp endpoints (check network egress and firewall rules).
When deploying, consider setting MTC (model-to-context) limits to control the amount of data fetched per query to avoid latency.
Use the env block to document and supply required variables; keep secrets secure (do not commit tokens in code).
If the server cannot bind to the desired port, check for port conflicts or run with elevated privileges depending on your environment.
Review ClickUp rate limits and implement retry/backoff in your client tooling to avoid hitting limits during bulk operations.

Related MCP Servers

inAI-wiki

🌍 The open-source Wikipedia of AI — 2M+ apps, agents, LLMs & datasets. Updated daily with tools, tutorials & news.

slack

Session-based Slack MCP for Claude and MCP clients: local-first workflows, secure-default HTTP.

mcpd

A ~3MB MCP daemon that exposes any script as a tool for Claude, Cursor & AI assistants

automcp

AutoMCP scaffolds your Model Context Protocol config from package.json deps

mcp-palette

Desktop application for managing Model Context Protocol servers (MCP). Provides a centralized interface to configure and manage MCP servers for use with LLMs and AI assistants such as Claude.

MCP -docker-guide

Complete guide to setting up Model Context Protocol (MCP) servers with Docker on Linux. Step-by-step tutorial for Claude Desktop, Cursor, and Windsurf integration.