Skip to main content

Access Smartschool courses, grades, assignments, and messages through the Model Context Protocol

Project description

Smartschool MCP Server

A Model Context Protocol (MCP) server that enables AI assistants to interact with the Smartschool platform, providing access to courses, grades, assignments, and messages.

Overview

This MCP server allows AI assistants like Claude to seamlessly access and retrieve information from Smartschool, a widely-used educational management platform in Belgium and the Netherlands. With this MCP server, students can ask their AI assistant about their grades, upcoming assignments, course information, and messages without leaving their conversation.

Features

The Smartschool MCP server provides the following tools:

📚 get_courses

Retrieve all available courses with teacher information.

  • Lists all enrolled courses
  • Includes teacher names for each course

📊 get_results

Fetch student grades and results with detailed information.

  • Supports pagination with limit and offset parameters
  • Filter by course name using course_filter
  • Optional detailed statistics (average, median) with include_details
  • Includes score descriptions, dates, and feedback

📝 get_future_tasks

Get upcoming assignments and tasks organized by date.

  • Shows all future assignments
  • Organized by date and course
  • Includes task descriptions and labels

📧 get_messages

Access mailbox messages with powerful filtering options.

  • Choose mailbox type: INBOX, SENT, DRAFT, etc.
  • Search messages by content with search_query
  • Filter by sender with sender_filter
  • Optional full message body with include_body
  • Pagination support

Installation

PyPI version Python 3.13+

Prerequisites

  • Python 3.13 or higher
  • uv package manager (recommended) or pip
  • A Smartschool account with valid credentials

Quick Install with MCP CLI (Recommended)

The easiest way to install and configure the server is using the MCP CLI:

# Install from PyPI and configure automatically
uvx mcp install smartschool-mcp \
  -e SMARTSCHOOL_USERNAME="your_username" \
  -e SMARTSCHOOL_PASSWORD="your_password" \
  -e SMARTSCHOOL_MAIN_URL="your-school.smartschool.be" \
  -e SMARTSCHOOL_MFA="YYYY-MM-DD"

This command will:

  • Install the package from PyPI
  • Add it to your Claude Desktop configuration
  • Set up the environment variables automatically

Manual Installation from PyPI

If you prefer to install manually and configure later:

# Using pip
pip install smartschool-mcp

# Using uv (recommended)
uv pip install smartschool-mcp

After manual installation, you'll need to configure Claude Desktop manually (see configuration section below).

Installation from Source

If you want to contribute or use the latest development version:

git clone https://github.com/MauroDruwel/Smartschool-MCP.git
cd Smartschool-MCP
uv sync

Configuration Parameters

Parameter Description Example
SMARTSCHOOL_USERNAME Your Smartschool username john.doe@student.school.be
SMARTSCHOOL_PASSWORD Your Smartschool password yourpassword123
SMARTSCHOOL_MAIN_URL Your school's Smartschool URL (without https://) school.smartschool.be
SMARTSCHOOL_MFA Your date of birth (YYYY-MM-DD format) 2008-01-15

Usage Examples

Once installed and configured with Claude Desktop or another MCP client, you can ask questions like:

  • "What are my recent grades?"
  • "Show me my upcoming assignments"
  • "What courses am I enrolled in?"
  • "Do I have any new messages?"
  • "What's my average grade in Math?"
  • "Show me messages from my teacher about the project"

Tool Usage Examples

Get courses:

get_courses()

Get recent grades:

get_results(limit=10, course_filter="Math", include_details=True)

Get upcoming assignments:

get_future_tasks()

Search messages:

get_messages(
    limit=20,
    search_query="homework",
    sender_filter="teacher",
    include_body=True
)

Claude Desktop Configuration

Add this configuration to your claude_desktop_config.json:

Option 1: Using uvx (Recommended)

{
  "mcpServers": {
    "smartschool": {
      "command": "uvx",
      "args": [
        "smartschool-mcp"
      ],
      "env": {
        "SMARTSCHOOL_USERNAME": "your_username",
        "SMARTSCHOOL_PASSWORD": "your_password",
        "SMARTSCHOOL_MAIN_URL": "your-school.smartschool.be",
        "SMARTSCHOOL_MFA": "YYYY-MM-DD"
      }
    }
  }
}

Option 2: Using Python module

{
  "mcpServers": {
    "smartschool": {
      "command": "python",
      "args": [
        "-m",
        "smartschool_mcp"
      ],
      "env": {
        "SMARTSCHOOL_USERNAME": "your_username",
        "SMARTSCHOOL_PASSWORD": "your_password",
        "SMARTSCHOOL_MAIN_URL": "your-school.smartschool.be",
        "SMARTSCHOOL_MFA": "YYYY-MM-DD"
      }
    }
  }
}

Option 3: From source (for development)

{
  "mcpServers": {
    "smartschool": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "C:\\Users\\YourUsername\\path\\to\\Smartschool-MCP",
        "main.py"
      ],
      "env": {
        "SMARTSCHOOL_USERNAME": "your_username",
        "SMARTSCHOOL_PASSWORD": "your_password",
        "SMARTSCHOOL_MAIN_URL": "your-school.smartschool.be",
        "SMARTSCHOOL_MFA": "YYYY-MM-DD"
      }
    }
  }
}

Note: Replace C:\Users\YourUsername\path\to\Smartschool-MCP with the actual absolute path where you cloned the repository.

Config file locations:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

Security Considerations

⚠️ Important Security Notes:

  • Your Smartschool credentials are stored in environment variables or configuration files
  • Never commit credentials to version control
  • Use environment variables or secure secret management in production
  • Consider using application-specific passwords if supported
  • The server only has read-only access to your Smartschool data
  • All communication happens locally between your AI assistant and the Smartschool API

Troubleshooting

Authentication Issues

  • Verify your credentials are correct
  • Ensure your MFA date (date of birth) is in the correct format: YYYY-MM-DD
  • Check that your school's URL is correct (without https://)

Connection Issues

  • Verify your internet connection
  • Check if Smartschool is accessible from your browser
  • Ensure no firewall is blocking the connection

Installation Issues

  • Make sure Python 3.13+ is installed
  • Verify uv is properly installed and in your PATH
  • Try running uv sync to reinstall dependencies

Development

Project Structure

Smartschool-MCP/
├── main.py              # Main MCP server implementation
├── pyproject.toml       # Project dependencies and metadata
├── README.md            # This file
└── uv.lock              # Locked dependencies

Dependencies

  • mcp[cli]>=1.9.4 - Model Context Protocol SDK
  • smartschool - Smartschool API wrapper (custom fork)

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

License

This project is open source and available under the MIT License.

Credits

Disclaimer

This is an unofficial tool and is not affiliated with, endorsed by, or connected to Smartschool or its parent company. Use at your own risk. Always ensure you comply with your school's terms of service and acceptable use policies.

Support

For issues, questions, or suggestions, please open an issue on GitHub.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

smartschool_mcp-0.1.4.tar.gz (25.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

smartschool_mcp-0.1.4-py3-none-any.whl (9.6 kB view details)

Uploaded Python 3

File details

Details for the file smartschool_mcp-0.1.4.tar.gz.

File metadata

  • Download URL: smartschool_mcp-0.1.4.tar.gz
  • Upload date:
  • Size: 25.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for smartschool_mcp-0.1.4.tar.gz
Algorithm Hash digest
SHA256 ac68d12c91fa1ec048b092e9fbb8abcad0f8a9a82c27586119707ebc710499f2
MD5 38000ad8566d4e0efb867647d02db068
BLAKE2b-256 43906fca25acf494964cdc2d865cf61b8e4e153cfe2fb14f38923be6e8f90d1c

See more details on using hashes here.

Provenance

The following attestation bundles were made for smartschool_mcp-0.1.4.tar.gz:

Publisher: publish.yml on MauroDruwel/Smartschool-MCP

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file smartschool_mcp-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for smartschool_mcp-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 c02b8966b0df27cdb48244146e4a4df336c2da64fca2906344ded22d9dd64c70
MD5 07d961ae89f75ec7641922c4ef486b6b
BLAKE2b-256 76eedcb5359d00dcbdeff2ff400153e9c1ed88f6b8f5b732e4f375431487670f

See more details on using hashes here.

Provenance

The following attestation bundles were made for smartschool_mcp-0.1.4-py3-none-any.whl:

Publisher: publish.yml on MauroDruwel/Smartschool-MCP

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page