Clockify MCP Server

Clockify MCP Server

An MCP server that lets LLMs interact with your Clockify workspace for time-tracking automation and reporting, enabling natural language logging of time entries, querying entries, and generating reports.

Category
访问服务器

README

Build Status Docker Image

<a href="https://glama.ai/mcp/servers/@wwwslinger/clockify-mcp"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@wwwslinger/clockify-mcp/badge" alt="Clockify MCP server" /> </a>

Clockify MCP Server

An MCP server that lets LLMs interact with your Clockify workspace for time-tracking automation and reporting. Use natural language to log time, query entries, and generate reports.

<p align="center"> <img src="assets/clockify_example.png" alt="Clockify Example" width="600" /> </p>

Features

Time Entry Management

  • addTimeEntry — Add time entries to a project, or start a running timer (omit end time)
  • updateTimeEntry — Update an existing time entry (description, project, times, tags, billable)
  • deleteTimeEntry — Delete a time entry by ID

Querying Time Entries

  • getTimeEntries — List time entries for the authenticated user (with date, project, and description filters)
  • getUserTimeEntries — List time entries for any user by their ID
  • getUserTimeEntriesByName — List time entries for a user by name (case-insensitive partial match)

Reports

  • getSummaryReport — Summary of hours grouped by user, project, client, task, tag, or date (Clockify Reports API)
  • getDetailedReport — Individual time entries with full metadata for a date range

Workspace Data

  • listProjects — List projects with filtering by name, archived status, and billable status
  • listUsers — List workspace users with filtering by name, email, and status
  • listTags — List all tags in the workspace
  • listClients — List all clients in the workspace

Setup

1. Get a Clockify API Key

  1. Log in to your Clockify account.
  2. Click your profile icon (top right) → Profile.
  3. Scroll to the API section and click Manage API keys.

<p align="center"> <img src="assets/Clockify-ManageAPIKeys.png" alt="Clockify Manage API Keys" width="600" /> </p>

  1. Click Generate to create a new API key, or copy your existing one.

<p align="center"> <img src="assets/Clockify-GenerateAPIKey.png" alt="Clockify Generate API Key" width="400" /> </p>

2. Configure Your LLM Client

Kiro CLI (local)

Clone the repo and add the following to your project's .kiro/settings/mcp.json (or your global ~/.kiro/settings/mcp.json):

{
  "mcpServers": {
    "clockify": {
      "command": "/path/to/node",
      "args": ["/path/to/clockify-mcp/build/index.js"],
      "env": {
        "CLOCKIFY_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Or docker pull ghcr.io/<REPO_USER>/clockify-mcp:latest and use

{
  "mcpServers": {
    "clockify": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e", "CLOCKIFY_API_KEY=<YOUR_API_KEY>",
        "ghcr.io/<REPO_USER>/clockify-mcp:latest"  
      ]
    }
  }
}

Cursor / Claude Desktop (Docker)

Add to your settings.json:

{
  "mcpServers": {
    "clockify-mcp": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "CLOCKIFY_API_KEY=<YOUR_API_KEY>",
        "ghcr.io/<REPO_USER>/clockify-mcp:latest"
      ]
    }
  }
}

Usage Tips

Project Caching (Recommended)

Tell your LLM:

"Create a cache of the list of Clockify projects and only refresh when a project isn't found, I request a refresh, or 24 hours has passed since it was refreshed."

This avoids an API call on every time entry and keeps interactions fast. The LLM will store something like this and use it for instant project ID lookups:

| Project Name                          | ID                       | Client         | Billable |
|---------------------------------------|--------------------------|----------------|----------|
| Acme - Website Redesign (Phase 2)     | 64a1b2c3d4e5f6a7b8c9d0e1 | Acme Corp      | Yes      |
| Presales-Engineering                  | 64b2c3d4e5f6a7b8c9d0e1f2 | Internal       | No       |
| Widget Co - Data Migration            | 64c3d4e5f6a7b8c9d0e1f2a3 | Widget Co      | Yes      |
| Internal Training                     | 64d4e5f6a7b8c9d0e1f2a3b4 | Internal       | No       |
| Globex - Mobile App                   | 64e5f6a7b8c9d0e1f2a3b4c5 | Globex Inc     | Yes      |
| Leave/PTO/Sick Leave                  | 64f6a7b8c9d0e1f2a3b4c5d6 | Internal       | No       |

Natural Language Examples

You can use partial project names — the LLM will fuzzy-match against the cached list:

Single entry:

Add a Clockify time entry: 9-10am, July 28, 2026; Acme; "Sprint review and deployment fixes"

Short form (partial project name):

Clockify: 8-8:30a on 2026-07-28 for Presales as "SOW Review"

Batch entries:

Add the following time entries to Clockify for July 28, 2026:
Acme: 11a-12:30p "Sprint review and database connections"
Widget Co: 9:30-11a "Data migration planning; schema review"
Presales: 12:30p-5p "Customer demo prep; proposal writing"

With semicolons for multiple activities:

Clockify time entry: 12-5p, July 27; Presales; "Sales call; SOW draft; competitor research"

Multiple entries, same project, out of order:

Add to Clockify for Presales on July 29:
8-9a "Morning standup and sprint planning"
2-4p "Architecture review with customer"
11a-12p "SOW revisions"

Reports:

Show me a summary of hours by project for last week.
How many hours did I log to Globex in July?

Docker Image

  • Image: ghcr.io/<REPO_USER>/clockify-mcp:latest
  • Pull:
    docker pull ghcr.io/<REPO_USER>/clockify-mcp:latest
    

Published automatically via GitHub Actions on every push to main.

Development

npm install
npm run build

The build output goes to build/index.js which is the entry point for the MCP server.

License

MIT — see LICENSE.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选