Tracker MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Tracker MCP Servershow today's schedule"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Tracker MCP Server
This is an MCP (Model Context Protocol) server designed to connect to your local tracker-server. It exposes endpoints like checking today's schedule, retrieving statistics, registering tasks, and managing timers directly to LLM clients (like Claude Desktop or Cursor).
Prerequisites
A running instance of
tracker-server(usually onhttp://localhost:3000).Python 3.11+ (if running locally) or Docker.
🚀 Running via Docker (Recommended)
When you deploy your MCP agent, you can hook it directly to the Docker image provided from the GitHub Container Registry.
Because tracker-server is running on your host machine locally, Docker needs to know how to reach it. The image defaults to http://host.docker.internal:3000 assuming you are on Mac/Windows or using Docker Desktop.
For Claude Desktop configuration (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"
]
}
}
}Note: Notice the
-iflag. Because MCP communicates over stdin/stdout (stdio), you must run the docker container interactively, but without a TTY (-t).
🛠Running Locally
If you are developing or simply prefer to run from source instead of Docker.
Setup the Virtual Environment:
cd tracker-mcp python -m venv venv source venv/bin/activate pip install -r requirements.txtRun the MCP Server manually:
# Make sure your tracker server is running! python server.pyNote: This will just block your terminal waiting for
stdioMCP JSON RPC commands. This is expected.Configure Claude Desktop (Local Mode):
{ "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 installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/egormak/tracker-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server