MCP Scheduler

by JorgeVanco

1 stars
99 downloads
Not rated
GitHub

About

An MCP server to provide tools with access to google calendar and google tasks to help you schedule your day and events.

Details

Author
JorgeVanco
GitHub stars
1
Downloads
99
Categories
Productivity

- Manage Google Calendar events (create, read, update).
- Manage Google Tasks (create tasks).
- OAuth 2.0 authentication with token caching.
- Minimal configuration – clone, place credentials, add config.
- Token auto-refresh support (token.json stored locally).

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MCP Scheduler
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install uv, clone the repository, and place a credentials.json file (with Google Calendar and Tasks APIs enabled) in the project root. Add the provided JSON configuration to your model's MCP server settings, replacing the directory path with the full path to the cloned folder. The server runs via uv and handles the OAuth 2.0 flow on first launch.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp scheduler": {
            "Scheduler": {
                "command": "uv",
                "args": [
                    "--directory",
                    "C:\\Path\\to\\Scheduler-MCP",
                    "run",
                    "-m",
                    "src.main"
                ]
            }
        }
    }
}

McpServers

{
    "Scheduler": {
        "command": "uv",
        "args": [
            "--directory",
            "C:\\Path\\to\\Scheduler-MCP",
            "run",
            "-m",
            "src.main"
        ]
    }
}

MCP Scheduler

This is an MCP server that provides tools to manage events in your google calendar and tasks.

Adding the MCP Server

Installation Steps

1. Install uv to manage the dependencies, as recomended by Model context protocol

2. Clone the Repository

    git clone https://github.com/JorgeVanco/Scheduler-MCP.git
    cd Scheduler-MCP
    

3. Configure Google API Credentials

- Go to the Google Cloud Console
- Create a new project
- Enable the Google Calendar API and Google Tasks API
- Create OAuth 2.0 credentials and download the credentials.json file
- Place the credentials.json file in the project root directory

4. Add the MCP config to the model configuration file
Add the following JSON configuration to the configuration file:

"mcpServers": {
    "Scheduler": {
        "command": "uv",
        "args": [
            "--directory",
            "C:\\Path\\to\\Scheduler-MCP",
            "run",
            "-m",
            "src.main"
        ]
    }
}

> Note Replace C:\\Path\\to\\Scheduler-MCP with the full path to the Scheduler-MCP folder

This configuration runs the src.main module using uv in the specified directory.

Usage

Once configured, your language model will be able to interact with Google Calendar and Google Tasks through this MCP server.

Example Commands

- "Schedule a meeting for tomorrow at 10:00 AM"
- "Show my events for this week"
- "Create a task to buy groceries"

Troubleshooting

Google Authentication

The first time the model starts the MCP server, a Google authentication window will pop up to request access to your calendars. Access tokens are stored in token.json to avoid logging in every time.

If you encounter errors, it might be because the token has expired. To fix this, delete the token.json file from the Scheduler-MCP folder.

> Coming Soon: A tool to automatically manage authentication tokens.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.