course-mcp
A local MCP server for referencing course files from a configured classes directory, allowing listing courses and their files safely.
README
course-mcp
course-mcp is a local Python MCP server for referencing course files from a
configured classes directory.
The project is currently focused on listing available courses and building the service layer needed to browse course files safely.
Current Features
- Loads
ROOT_DIRfrom.envor the process environment. - Restricts file access to paths inside
ROOT_DIR. - Provides a
FileServicefor safe file reads. - Provides a
CourseServicefor course/file listing. - Exposes an MCP tool:
list-courses: lists the top-level course directories underROOT_DIR.list-course-files: lists the direct files inside a course directory.
Project Layout
src/course_mcp/
server.py MCP server boundary
config/ environment/config loading
services/
file_service.py safe filesystem access
course_service.py course-oriented operations
models/ simple data models
tests/ pytest tests
skills/ project-specific agent skills
Configuration
Create a .env file at the project root:
ROOT_DIR="/Users/markseeliger/Desktop/Classes/UMD"
ROOT_DIR must point to an existing directory. Each direct child directory is
treated as a course.
You can also pass ROOT_DIR directly through the environment instead of using
.env.
Run Locally
From this project directory:
uv run course-mcp
Because MCP servers run over stdio, they are usually launched by an MCP client rather than run directly by hand.
Install In Codex
Register the server with Codex:
codex mcp add course-mcp \
--env ROOT_DIR=/Users/markseeliger/Desktop/Classes/UMD \
-- uv --directory /Users/markseeliger/Desktop/Coding/create-python-server/course_mcp run course-mcp
Verify the registration:
codex mcp get course-mcp
Or refresh the registration with the project script:
ROOT_DIR=/Users/markseeliger/Desktop/Classes/UMD ./scripts/update_mcp_server.sh
If you change MCP tools, restart Codex or start a new Codex session so the tool list is reloaded.
Development
Run the test suite:
uv run pytest
Run a compile check:
python3 -m compileall src/course_mcp tests
Debug with MCP Inspector:
npx @modelcontextprotocol/inspector uv --directory /Users/markseeliger/Desktop/Coding/create-python-server/course_mcp run course-mcp
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.
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.
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.
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.