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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。