Ed Discussions MCP Server
Enables AI assistants to interact with Ed Discussions (EdStem) course discussions, manage threads, comments, and facilitate Q&A, with tools for analytics and read status control.
README
Ed Discussions MCP Server
A comprehensive Model Context Protocol (MCP) server for Ed Discussions (EdStem) platform, enabling AI assistants to interact with course discussions, manage threads, comments, and facilitate Q&A.
Status
✅ Functional - Core MCP server with 16 tools implemented and tested
Features
Implemented Tools (16)
System Tools
ed_health_check- Check API connectivity and authentication
User Tools
ed_get_current_user- Get authenticated user information
Course Tools
ed_list_courses- List all enrolled coursesed_get_course- Get detailed course information
Thread Tools
ed_list_threads- List threads with filtering and sortinged_get_thread- Get thread details (with optional mark_as_read control)ed_create_thread- Create new question/post/announcemented_update_thread- Update thread content or settingsed_delete_thread- Delete a threaded_mark_thread_read- Mark a thread as readed_mark_thread_unread- Mark a thread as unread
Comment Tools
ed_list_comments- List all comments (thread + answer replies) with participant metadataed_create_comment- Add comment to threaded_update_comment- Update/endorse commented_delete_comment- Remove comment
Analytics Tools
ed_course_activity_stats- Generate student-only leaderboards for activity, answers, hearts, questions, and posts
Setup
Prerequisites
- Node.js 18+
- Ed Discussions account with API access
- API token from your institution's Ed instance
Installation
-
Get your Ed API token:
- Log into Ed Discussions
- Navigate to: https://us.edstem.org/settings/api-tokens
- Generate a new token
-
Clone and configure:
git clone https://github.com/yourusername/mcp-ed.git
cd mcp-ed
- Create
.envfile:
ED_API_TOKEN=your-token-here
ED_DOMAIN=edstem.org
ED_REGION=us # or your region (au, uk, etc.)
- Install and build:
npm install
npm run build
- Test connection:
node build/testConnection.js # Test API connection
node build/testMCPServer.js # Test MCP server
Usage
With Claude Desktop
Add to your Claude Desktop configuration (%APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"ed-discussions": {
"command": "node",
"args": ["/path/to/mcp-ed/build/index.js"],
"env": {
"ED_API_TOKEN": "your-token-here",
"ED_DOMAIN": "edstem.org",
"ED_REGION": "us"
}
}
}
}
Standalone Server
npm start # Runs the MCP server on stdio
Using the Inspector
npx @modelcontextprotocol/inspector build/index.js
API Examples
List courses
{
"name": "ed_list_courses",
"arguments": {}
}
Get threads from a course
{
"name": "ed_list_threads",
"arguments": {
"course_id": "81559",
"limit": 10,
"sort": "new",
"filter": "unread"
}
}
Get thread without marking as read
{
"name": "ed_get_thread",
"arguments": {
"course_id": "81559",
"thread_id": "6873464",
"mark_as_read": false // Prevents marking thread as seen
}
}
Generate course activity stats
{
"name": "ed_course_activity_stats",
"arguments": {
"course_id": "81559",
"max_entries": 20
}
}
Create a new thread
{
"name": "ed_create_thread",
"arguments": {
"course_id": "81559",
"type": "question",
"title": "Help with assignment",
"content": "I'm having trouble with...",
"category": "Assignments",
"is_anonymous": false
}
}
Development
Project Structure
mcp-ed/
├── src/
│ ├── index.ts # MCP server implementation
│ ├── edClient.ts # Ed API client
│ ├── testConnection.ts # API connection tester
│ └── testMCPServer.ts # MCP server tester
├── build/ # Compiled JavaScript
├── .env # API credentials (git-ignored)
└── package.json
Scripts
npm run build # Compile TypeScript
npm run dev:watch # Development mode with auto-rebuild
npm run test # Run tests
npm run lint # Lint code
npm start # Run MCP server
Testing
The server includes comprehensive test suites:
testConnection.ts- Tests Ed API connectivitytestMCPServer.ts- Tests all MCP tools
Architecture
Built on the Model Context Protocol SDK, following the successful patterns from the Canvas LMS MCP implementation:
- TypeScript for type safety
- Axios for HTTP requests
- MCP SDK for protocol implementation
- Modular design for easy extension
Read Status Control
The Ed MCP Server provides fine-grained control over thread read status:
- Read without marking: Set
mark_as_read: falsewhen callinged_get_thread - Default behavior: Threads are marked as read when accessed (preserves normal Ed behavior)
- Manual control: Use
ed_mark_thread_readanded_mark_thread_unreadtools - Preserves privacy: Reading threads without marking them prevents others from knowing you've read them
Security
- API tokens are stored in environment variables
- Never commit
.envfiles - Supports anonymous posting where allowed
- Respects course privacy settings
Roadmap
Near-term
- [ ] Add search functionality
- [ ] Implement file upload support
- [ ] Add bulk operations
- [ ] Create notification system
Long-term
- [ ] WebSocket support for real-time updates
- [ ] Analytics and reporting tools
- [ ] LMS integration features
- [ ] Advanced filtering and sorting
Contributing
Contributions welcome! Please:
- Fork the repository
- Create a feature branch
- Test thoroughly
- Submit a pull request
Support
- Issues: https://github.com/yourusername/mcp-ed/issues
- Discussions: Use GitHub Discussions for questions
License
MIT - See LICENSE file for details
Acknowledgments
- Built on patterns from Canvas LMS MCP
- Uses the Model Context Protocol SDK
- Thanks to the Ed Discussions team for API access
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.