TimeCamp MCP Server

TimeCamp MCP Server

A Model Context Protocol server that provides time tracking integration with TimeCamp, allowing AI assistants to create, retrieve, update, and delete time entries through natural language commands.

Category
访问服务器

README

TimeCamp MCP Server

  • Why TS not Python? Official client, more materials, support for Cloudflare workers.
  • Why hosted and not local only? Easier to use, users don't need to install it.
  • Why Cloudflare Workers? Cheap & easy.

This MCP server provides the following tools for TimeCamp integration:

  • add_timecamp_time_entry - Create a new time entry with start time, end time, note, and optional task
  • get_timecamp_time_entries - Retrieve time entries for a specified date range
  • get_timecamp_tasks - Fetch all available TimeCamp projects and tasks
  • delete_timecamp_time_entry - Delete a specific time entry by ID
  • update_timecamp_time_entry - Update an existing time entry (time, note, or task assignment)

Example prompt

Create Timecamp time entries based on these tasks I did. 
I write tasks by putting -HH:MM, which is the end time for the task, so each time entry should take from end end time of previous entry.
Try to match timecamp task, so first you have to fetch my timecamp tasks.
Note should be single sentence in English with 3-12 words.
Ignore "[minutes:: ...]" as this is estimate.

- [x] -9:43 emails & org [completion:: 2025-06-21]
- [x] -12:10 #tech new version of reports [[(project) XYZ]] [completion:: 2025-06-21]
- [x] -12:58 (evening) Buy shoes + relax [completion:: 2025-06-21] 
- [x] -14:30 relax [completion:: 2025-06-21]
- [x] -15:30 #tech Notifications still not working for one more person from our group [completion:: 2025-06-21]
- [x] -15:40 I don't remember [completion:: 2025-06-21] 
- [x] -17:09 #tech Client - database connection problem [[(process) Technical support]] [minutes:: 15] [completion:: 2025-06-21]
- [x] -17:35 break [completion:: 2025-06-21]
- [x] -19:17 #tech Client [[(project) Client]] [[(process) Technical support]] [minutes:: 10] [completion:: 2025-06-21]
	- - [x] -19:21 (evening) Fill timesheet [completion:: 2025-06-21]

Setup & run

Local

pnpm start
npx mcp-remote http://localhost:8787/sse --header "Authorization: Bearer <api_token>"

Deploy

pnpm dlx wrangler@latest deploy
pnpm dlx wrangler@latest tail
npx mcp-remote https://my-mcp-server.timecamp-s-a.workers.dev/sse --header "Authorization: Bearer <api_token>"

Test

pnpm dlx @modelcontextprotocol/inspector@latest

Connect Claude Desktop to your MCP server

You can also connect to your remote MCP server from local MCP clients, by using the mcp-remote proxy.

To connect to your MCP server from Claude Desktop, follow Anthropic's Quickstart and within Claude Desktop go to Settings > Developer > Edit Config.

Update with this configuration:

{
  "mcpServers": {
    "timecamp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://my-mcp-server.timecamp-s-a.workers.dev/sse", // or http://localhost:8787/sse
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer <auth-token>"
      }
    },
    "timecamp_url": { // if MCP client supports url
      "url": "https://my-mcp-server.timecamp-s-a.workers.dev/sse",
      "headers": {
        "Authorization": "Bearer <auth-token>...."
      }
    },
  }
}

Restart Claude and you should see the tools become available.

If you have MacOS Claude Desktop - 'Server transport closed unexpectedly' see https://github.com/modelcontextprotocol/servers/issues/1748#issuecomment-2896004925.

Not yet implemented

  • Oauth authorization (https://github.com/huanshenyi/mcp-server-bearer-auth/tree/main)
  • Problem with MCP using URL in Cursor

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