Tracker MCP Server
Servidor MCP de Tracker
Este es un servidor MCP (Model Context Protocol) diseñado para conectarse a tu tracker-server local. Expone puntos de conexión como consultar el horario de hoy, obtener estadísticas, registrar tareas y gestionar temporizadores directamente a clientes LLM (como Claude Desktop o Cursor).
Requisitos previos
Una instancia de
tracker-serveren ejecución (normalmente enhttp://localhost:3000).Python 3.11+ (si se ejecuta localmente) o Docker.
Related MCP server: mcp-server-tasktracker
🚀 Ejecución mediante Docker (Recomendado)
Cuando despliegues tu agente MCP, puedes conectarlo directamente a la imagen de Docker proporcionada desde el Registro de Contenedores de GitHub.
Debido a que tracker-server se está ejecutando en tu máquina local, Docker necesita saber cómo acceder a él. La imagen utiliza por defecto http://host.docker.internal:3000 asumiendo que estás en Mac/Windows o utilizando Docker Desktop.
Para la configuración de Claude Desktop (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"
]
}
}
}Nota: Observa la bandera
-i. Debido a que MCP se comunica a través de stdin/stdout (stdio), debes ejecutar el contenedor de Docker de forma interactiva, pero sin un TTY (-t).
🛠 Ejecución local
Si estás desarrollando o simplemente prefieres ejecutar desde el código fuente en lugar de Docker.
Configura el entorno virtual:
cd tracker-mcp
python -m venv venv
source venv/bin/activate
pip install -r requirements.txtEjecuta el servidor MCP manualmente:
# Make sure your tracker server is running!
python server.pyNota: Esto simplemente bloqueará tu terminal esperando comandos JSON RPC de MCP a través de stdio. Esto es lo esperado.
Configura Claude Desktop (Modo local):
{
"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"
}
}
}
}Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
timesheet.io MCP server - manage timers, projects, tasks and reports
Toggl 2.0 MCP server for tasks, projects, time entries, and workspace operations.
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.
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.116 npmMIT
- AlicenseNot gradedqualityCmaintenanceAn 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
- AlicenseNot gradedqualityDmaintenanceAn 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
- AlicenseBqualityBmaintenanceEnables MCP clients to query a self-hosted TimeTracker instance over its /api/v1 REST API, exposing tracked hours, per-day and per-project summaries, projects, clients, tasks, search, and active-timer status in natural language. Optionally registers write tools to start, stop, pause, resume, and create timers or time entries when write mode is enabled.10MIT