Courses MCP Server
Enables LLMs to interact with FIT CTU course materials, including listing subjects, navigating subpages, reading content as Markdown, and performing keyword searches.
README
Courses MCP Server
An MCP (Model Context Protocol) server designed for the Faculty of Information Technology, Czech Technical University (FIT CTU) course materials site: courses.fit.cvut.cz.
It enables LLMs (such as Cline, Cursor, or Open WebUI) to list subjects, navigate their subpages (lectures, labs, exams), read materials converted to clean Markdown, and perform quick keyword searches across subjects.
Features
- Dual Authentication: Supports logging in using pre-fetched browser session cookies or CTU credentials (username and password) with automatic cookie persistence.
- Enrolled Semester Courses: Detects and lists subjects currently enrolled by the student.
- Static Site Navigation: Crawls and resolves the navigation sidebar (PagesFIT/MkDocs) of any course.
- Clean Markdown: Isolates primary content sections (e.g.
<main>,<article>) and converts them to readable, clean Markdown. - Indexed Keyword Search: Iterates through course pages and searches for keywords, with local caching to speed up consecutive searches.
Installation
- Clone or copy this repository into your chosen directory.
- Initialize the Python virtual environment and install the required dependencies:
python3 -m venv venv ./venv/bin/pip install -r requirements.txt
Configuration
Duplicate the .env.example file to .env and set up your preferred authentication method:
# OPTION 1: Set session cookies directly (Recommended if you use MFA)
COURSES_COOKIES="oauth_access_token=...; oauth_refresh_token=...; oauth_username=your-username"
# OPTION 2: Set credentials for automatic OAuth login handshake
COURSES_USERNAME="your-username"
COURSES_PASSWORD="your-ctu-password"
Registered MCP Tools
The server exposes the following tools:
login(username, password): Performs CTU login, updates session cookies, and writes the retrieved cookies to the.envfile for automatic persistent logins.list_courses(cookies): Lists subjects taught at FIT. If authenticated, separates your current semester courses from all other catalog subjects.get_course_index(course_code): Retrieves all available subpages (paths and titles) from the sidebar menu of a course.get_page_content(course_code, page_path): Fetches a specific course subpage and returns its main section in Markdown format.search_course_content(course_code, query): Scrapes (or reads from cache) all pages of a course and returns matching search snippets.download_course_file(course_code, file_path, cookies): Downloads any linked slide (PDF), code, or file from the course portal.
Exposed MCP Resources
The server exposes the following read-only resources:
courses://list: Returns the list of subjects/courses.courses://{course_code}/index: Returns the navigation index sidebar of a subject.courses://{course_code}/pages/{page_path}: Returns the content of a specific course subpage in Markdown. (Note: For nested paths, URL-encode the slashes as%2F, e.g.,lectures%2Findex.html)
Global MCP Integration
Add this configuration to your local MCP client settings (e.g. mcp_config.json):
{
"mcpServers": {
"courses": {
"command": "/home/dzendys_/Downloads/courses/venv/bin/python",
"args": ["/home/dzendys_/Downloads/courses/mcp_server.py"]
}
}
}
License
Created for educational and utility purposes for students and teachers of FIT ČVUT.
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.