Wilma MCP Server
An MCP server for the Wilma school communication platform, enabling AI assistants to view schedules, read and send messages, and manage inbox.
README
Wilma MCP Server
An MCP (Model Context Protocol) server for Wilma - the Finnish school communication platform by Visma. This allows Claude and other MCP-compatible AI assistants to interact with school data including schedules, messages, and more.
Features
- Schedule - View daily or weekly timetables with subjects, times, and teachers
- Messages - Read inbox messages with read/unread status, view full content, mark as read
- Recipients - List available message recipients (teachers, staff)
- Send Messages - Compose and send messages to teachers
Prerequisites
- Python 3.11 or higher
- A Wilma account (student, guardian, or teacher)
- Your school's Wilma URL (e.g.,
https://yourschool.inschool.fi)
Installation
# Clone the repository
git clone https://github.com/jessemc98/wilma-mcp.git
cd wilma-mcp
# Create virtual environment
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install the package
pip install -e .
Configuration
Create a .env file with your Wilma credentials:
cp .env.example .env
Edit .env:
WILMA_BASE_URL=https://yourschool.inschool.fi
WILMA_USERNAME=your_username
WILMA_PASSWORD=your_password
Security Note: Never commit your
.envfile to version control.
Usage with OpenClaw
If you use OpenClaw, this project includes a SKILL.md that automatically teaches your agent how to use the Wilma MCP tools.
- Complete the Installation and Configuration steps above.
- Add the MCP server to your Claude Code settings (
~/.claude.jsonor project.mcp.json):
{
"mcpServers": {
"wilma": {
"command": "/path/to/wilma-mcp/venv/bin/python",
"args": ["-m", "wilma_mcp.server"],
"cwd": "/path/to/wilma-mcp"
}
}
}
- Place or symlink the
SKILL.mdinto your OpenClaw skills directory so the agent can discover it.
Usage with Claude Desktop
Add the server to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"wilma": {
"command": "/path/to/wilma-mcp/venv/bin/python",
"args": ["-m", "wilma_mcp.server"],
"cwd": "/path/to/wilma-mcp"
}
}
}
Restart Claude Desktop after updating the configuration.
Available Tools
get_schedule
Get the school schedule for a specific date.
Parameters:
date_str(optional): Date to get schedule for. Defaults to "today".- Supports: "today", "tomorrow", "yesterday"
- Weekday names: "monday", "tuesday", etc. (English or Finnish)
- Date formats: "2024-03-15", "15.3.2024"
Example: "What's my schedule for Monday?"
get_week_schedule
Get the schedule for a full week.
Parameters:
start_date(optional): Start date of the week. Defaults to today.
Example: "Show me next week's schedule"
get_messages
Get list of messages from inbox. Each message shows a read/unread indicator (📖 read, 📬 unread).
Parameters:
folder(optional): Folder name - "inbox", "sent", or "archive". Defaults to "inbox".limit(optional): Maximum messages to return. Defaults to 20.
Example: "Check my messages"
get_message
Read a specific message with full content. Note: viewing a message automatically marks it as read on the Wilma server.
Parameters:
message_id: The ID of the message to read.
Example: "Read message 12345"
set_message_read
Explicitly mark a message as read. Useful for marking messages as read without reading their full content. Wilma does not support marking messages as unread — this is a platform limitation.
Parameters:
message_id: The ID of the message to mark as read.
Example: "Mark message 12345 as read"
get_recipients
Get list of available message recipients (teachers, staff).
Example: "Who can I send messages to?"
send_message
Send a new message to a teacher or staff member.
Parameters:
recipient_id: ID of the recipient (useget_recipientsto find IDs)subject: Message subjectbody: Message body/contentreply_to_id(optional): Message ID if this is a reply
Example: "Send a message to teacher 123 about homework"
reply_to_message
Reply to an existing message. This is the preferred way to reply since it handles recipient resolution automatically via Wilma's reply form, without needing to look up recipient IDs.
Parameters:
message_id: ID of the message to reply to (fromget_messages)body: Reply message body/content
Example: "Reply to message 12345 saying I'll attend"
Example Conversations
Once configured, you can ask Claude:
- "What's my schedule today?"
- "Do I have any classes on Friday?"
- "Show me my unread messages"
- "Read the message from my teacher"
- "What time does school start tomorrow?"
Technical Notes
- Wilma has no official public API. This server reverse-engineers the web interface.
- Authentication uses session cookies obtained via the login flow.
- Schedule data is extracted from embedded JavaScript in the schedule page.
- Message lists use a JSON endpoint; individual messages require HTML parsing.
- Read/unread tracking: Wilma's JSON API includes a
Statusfield per message — truthy means unread, falsy/absent means read. Viewing a message (GET request) marks it as read server-side. There is no API to mark a message as unread. - The server may need updates if Wilma's web interface changes.
Development
# Install with dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
Future Features (Planned)
- Grades and assessments
- Absence/attendance records
- Upcoming exams
- School news/announcements
- Course listings
License
MIT License - see LICENSE file.
Disclaimer
This is an unofficial project and is not affiliated with or endorsed by Visma. Use at your own risk. Be respectful of Wilma's terms of service and rate limits.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.