Clockify MCP server

The Clockify MCP Server integrates with AI tools to help you manage time entries in Clockify. This server enables you to register time entries by simply sending prompts to a Large Language Model (LLM), streamlining your time tracking workflow.

Installation Options

Via Smithery (Recommended)

You can quickly install the Clockify MCP Server for Claude Desktop using Smithery:

npx -y @smithery/cli install @https-eduardo/clockify-mcp-server --client claude

Manual Installation

If you prefer manual installation, follow these steps:

1. First, install ts-node globally:

npm i -g ts-node

2. Update your Claude Desktop configuration by adding the MCP server to your claude_desktop_config:

{
  "mcpServers": {
    "clockify-time-entries": {
      "command": "ts-node",
      "args": ["ABSOLUTE_PATH/src/index.ts"],
      "env": {
        "CLOCKIFY_API_URL": "https://api.clockify.me/api/v1",
        "CLOCKIFY_API_TOKEN": "YOUR_CLOCKIFY_API_TOKEN_HERE"
      }
    }
  }
}

3. Replace "ABSOLUTE_PATH" with the actual path to the server files on your system.
4. Replace "YOUR_CLOCKIFY_API_TOKEN_HERE" with your personal Clockify API token.

Alternative Setup

You can also compile the TypeScript code before running:

1. Compile the code using the TypeScript compiler:

tsc

2. Then modify your Claude Desktop configuration to use the compiled JavaScript version:

{
  "mcpServers": {
    "clockify-time-entries": {
      "command": "node",
      "args": ["ABSOLUTE_PATH/dist/index.js"],
      "env": {
        "CLOCKIFY_API_URL": "https://api.clockify.me/api/v1",
        "CLOCKIFY_API_TOKEN": "YOUR_CLOCKIFY_API_TOKEN_HERE"
      }
    }
  }
}

Usage

After installation, you can interact with Clockify through your LLM interface (like Claude). The server enables you to create time entries by simply describing what you worked on in natural language.

For example, you might send a prompt like:

• "Log 2 hours of work on project X from 9 AM to 11 AM today"
• "Create a time entry for meeting with client Y yesterday from 2-3 PM"

The AI will interpret your request and use the MCP Server to create the appropriate time entry in your Clockify account.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.