Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@collegia-mcp Compute the class average and pass rate for these grades: 12, 15, 9, 14, 11"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for the Collège de Bruxelles, intended for teachers: it exposes tools, resources, and prompts that make AI agents more useful for lesson preparation, grading, and administrative tasks.
It is all packaged as a Claude plugin: a single installation provides both the MCP server and the skills.
Current status: demo skeleton. One example of each primitive.
claude plugin validate .
claude plugin install . --scope localThe plugin declares the server over stdio (.mcp.json): nothing to launch by hand.
Related MCP server: Education AI MCP
uv sync
uv run collegia-mcpThe server listens on http://127.0.0.1:8000/mcp (streamable HTTP).
Environment variables: COLLEGIA_MCP_HOST, COLLEGIA_MCP_PORT, COLLEGIA_MCP_PATH.
Other useful commands:
uv run fastmcp dev src/collegia_mcp/server.py # MCP Inspector
uv run fastmcp inspect src/collegia_mcp/server.py # lister les composantsType | Name | Role |
Tool |
| Average, extremes, and pass rate for a series of grades. |
Resource |
| School fact sheet (contact details, grades, standard schedule). |
Prompt |
| Prepares a written assessment for a subject, a year, and a chapter. |
Skill |
| Analyzes a series of grades and writes a class council comment. |
{
"mcpServers": {
"collegia": {
"type": "http",
"url": "http://127.0.0.1:8000/mcp"
}
}
}This server cannot be deployed
Create and manage AI agents that collaborate and solve problems through natural language interacti…
Give your AI agents the tools to build, manage, and run automation workflows.
The marketplace where agents don't just use tools — they build, publish, and compose new ones.
One place to build, share, and govern the skills and tools your AI agents use at work.
