villaume/infomentor_mcp
3.2
If you are the rightful owner of infomentor_mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Infomentor MCP server is designed to streamline administrative tasks by leveraging the capabilities of Language Learning Models (LLMs) and intelligent agents.
infomentor_mcp
Infomentor MCP server - An attempt to offload admin things to LLMs/Agents
Installation
Install dependencies using uv:
uv sync
This will create a virtual environment and install all required packages from pyproject.toml
and uv.lock
.
Setup Environment Variables
Create a .env
file in the project root with your Infomentor credentials:
INFOMENTOR_USERNAME=your_username
INFOMENTOR_PASSWORD=your_password
INFOMENTOR_GROUP_1_ID=your_group_1_id
INFOMENTOR_GROUP_2_ID=your_group_2_id
INFOMENTOR_PUPIL_1_ID=your_pupil_1_id
INFOMENTOR_PUPIL_2_ID=your_pupil_2_id
Finding the IDs: Go to Infomentor on your computer - In the developer view > Javascript console check for the Ids:
Pupil IDs:
Group IDs:
Running the server
- Start the MCP server:
uv run python main.py
- In another terminal, expose it with ngrok:
ngrok http 8000
- Copy the ngrok URL from the output (e.g.,
https://xxxx-xxxx.ngrok-free.app
)
Testing with MCP Inspector
- Start the inspector:
npx @modelcontextprotocol/inspector
- Connect using:
https://YOUR-NGROK-URL.ngrok-free.app/sse
- Protocol: Select "SSE" in the dropdown
- Note: Use the
/sse
path (this is the SSE endpoint) - Make sure to use the current ngrok URL each time (they change on restart)
Using the MCP server
In claude for instance: