EdStem MCP
Enables querying Ed Discussion posts via Claude. Uses search, Cohere reranking, and thread retrieval to provide cited answers.
README
EdStem MCP
An MCP server that lets you ask Claude any question and have it pull the answer from your Ed Discussion (edstem.org) posts. It searches Ed's live API, reranks the hits with Cohere Rerank 3.5 for relevance, and hands the most relevant threads to Claude, which reads them and writes a cited answer.
How it works
you ask Claude ─▶ list_courses ─▶ search_ed (Ed keyword search ─▶ Cohere rerank)
│
▼
get_ed_thread (full thread, markdown)
│
▼
Claude synthesizes a cited answer
Cohere is used only as a second-stage reranker — not for embeddings or answer
generation. If COHERE_API_KEY is unset, search still works using Ed's native
ordering.
Tools
| Tool | What it does |
|---|---|
list_courses() |
List your Ed courses and their course_ids. |
search_ed(course_id, query, limit=20) |
Keyword search + Cohere rerank; returns thread summaries with relevance scores. |
get_ed_thread(thread_id) |
Full thread (question + answers + comments) as markdown. |
recent_ed_threads(course_id, limit=20) |
Most recent threads in a course. |
There's also an answer_from_ed prompt that scripts the search→read→cite flow.
Setup
1. Get your keys
- Ed API token: https://edstem.org/us/settings/api-tokens
- Cohere API key (optional but recommended): https://dashboard.cohere.com/api-keys
2. Install
With uv (recommended):
uv sync
Or with pip:
python -m venv .venv && source .venv/bin/activate
pip install -e .
3. Configure credentials
Copy .env.example to .env and fill it in:
cp .env.example .env
ED_API_TOKEN=your-ed-token
COHERE_API_KEY=your-cohere-key
# EU users: ED_API_BASE=https://eu.edstem.org/api/
Connect to Claude Code
Pass the credentials inline (no .env needed):
claude mcp add edstem \
-e ED_API_TOKEN=your-ed-token \
-e COHERE_API_KEY=your-cohere-key \
-- uv run edstem-mcp
If you installed with pip into a venv, replace uv run edstem-mcp with the path
to the installed edstem-mcp executable (e.g. .venv/bin/edstem-mcp).
Then just ask, e.g. "What did the staff say about the HW3 deadline on Ed?"
Develop / debug
Exercise the tools in the MCP inspector:
uv run mcp dev src/edstem_mcp/server.py
Notes
- The Ed API is unofficial and in beta; endpoints may change.
- Keep
.envout of version control (already in.gitignore).
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.