Tracker MCP Server
Tracker MCP 服务器
这是一个旨在连接到您的本地 tracker-server 的 MCP(模型上下文协议)服务器。它向 LLM 客户端(如 Claude Desktop 或 Cursor)直接公开了诸如检查今日日程、检索统计信息、注册任务和管理计时器等端点。
先决条件
一个正在运行的
tracker-server实例(通常在http://localhost:3000)。Python 3.11+(如果本地运行)或 Docker。
Related MCP server: mcp-server-tasktracker
🚀 通过 Docker 运行(推荐)
当您部署 MCP 代理时,可以直接将其挂载到 GitHub 容器注册表中提供的 Docker 镜像上。
由于 tracker-server 在您的本地主机上运行,Docker 需要知道如何访问它。该镜像默认使用 http://host.docker.internal:3000,前提是您使用的是 Mac/Windows 或 Docker Desktop。
Claude Desktop 配置 (claude_desktop_config.json):
{
"mcpServers": {
"tracker-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"TRACKER_API_URL=http://host.docker.internal:3000",
"ghcr.io/makegorka/tracker-mcp:latest"
]
}
}
}注意:请留意
-i标志。由于 MCP 通过 stdin/stdout (stdio) 进行通信,您必须以交互方式运行 docker 容器,但不能使用 TTY (-t)。
🛠 本地运行
如果您正在进行开发,或者只是更喜欢从源代码运行而不是使用 Docker。
设置虚拟环境:
cd tracker-mcp
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt手动运行 MCP 服务器:
# Make sure your tracker server is running!
python server.py注意:这将阻塞您的终端以等待 stdio MCP JSON RPC 命令。这是预期行为。
配置 Claude Desktop(本地模式):
{
"mcpServers": {
"tracker-mcp": {
"command": "/absolute/path/to/tracker-mcp/venv/bin/python",
"args": [
"/absolute/path/to/tracker-mcp/server.py"
],
"env": {
"TRACKER_API_URL": "http://localhost:3000"
}
}
}
}This server cannot be deployed
Maintenance
Related MCP Connectors
- mcp-serverOAuthio.klokin
MCP server exposing klokin time-tracking operations (employees, time entries, stores) to AI clients.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Track Keito time entries and LLM costs from AI agents.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables LLM clients to manage tasks, timers, and notes in Rhizm through natural language commands. It provides tools for task operations, time tracking, and note management via API integration.114 npmMIT
- AlicenseNot gradedqualityAmaintenanceAn MCP server that exposes the full Task-Tracker REST API as MCP tools, enabling AI agents to manage trackers, tasks, notes, checklists, and projects conversationally.MIT
- AlicenseBqualityCmaintenanceEnables AI clients to create and manage tasks via a local REST API by converting natural language into HTTP requests through the Model Context Protocol.1MIT
- AlicenseNot gradedqualityBmaintenanceAn 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.MIT