Khan Academy MCP Server

Khan Academy MCP Server

Enables AI assistants to search, browse, and read Khan Academy's educational content, including courses, articles, and video transcripts. It provides tools to navigate the subject hierarchy and retrieve detailed metadata without requiring an API key.

Category
Visit Server

README

<p align="center"> <img src="assets/khan-logo.png" alt="Khan Academy" width="400"> </p>

Khan Academy MCP Server

An open-source Model Context Protocol (MCP) server that lets AI assistants search, browse, and read Khan Academy's educational content. No API key required.

Quick Start

npx khanacademy-mcp

Or install globally:

npm install -g khanacademy-mcp
khanacademy-mcp

Claude Desktop Configuration

Add this to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "khanacademy": {
      "command": "npx",
      "args": ["-y", "khanacademy-mcp"]
    }
  }
}

Tools

Tool Description
search Search Khan Academy for videos, articles, exercises, and courses
list_subjects List all top-level subjects and popular courses
get_topic_tree Browse the subject/topic hierarchy by slug with configurable depth
get_content Get details about a specific content item (video, article, exercise)
get_course Get full course structure with units, lessons, and content items
get_transcript Get video transcripts (timestamped or full text)
get_article Read the full text content of a Khan Academy article
get_lesson Get all content items in a specific lesson
embed_video Embed a video with thumbnail image, metadata, chapters, and optional transcript
get_exercise Get exercise details with related study content (videos, articles) and practice URL
get_quiz List all quizzes, unit tests, and course challenge for a course with prep material
study_guide Build a structured study plan for any topic

Tool Details

search

query: string    — Search query (e.g., "photosynthesis", "quadratic formula")
limit?: number   — Max results (1-30, default: 10)

list_subjects

No parameters. Returns all top-level subjects and popular courses.

get_topic_tree

slug: string     — Topic slug (e.g., "math", "science/biology")
depth?: number   — Levels to fetch (0-3, default: 1)

get_content

slug: string     — Content slug or full URL

get_course

slug: string     — Course slug or URL (e.g., "math/algebra")

get_transcript

slug: string     — Video slug, KA URL, YouTube URL, or YouTube ID
language?: string — Language code (default: "en")
format?: string  — "full", "timestamped", or "both" (default: "full")

get_article

slug: string     — Article slug or full URL (articles have "/a/" in the path)

get_lesson

slug: string     — Lesson slug or full URL

embed_video

slug: string              — Video slug, KA URL, YouTube URL, or YouTube ID
include_transcript?: bool — Include the full transcript (default: false)
language?: string         — Language code for transcript (default: "en")

get_exercise

slug: string     — Exercise slug or full URL (exercises have "/e/" in the path)

get_quiz

slug: string     — Course slug or URL (e.g., "math/algebra")
kind?: string    — "all", "quiz", "unit-test", or "course-challenge" (default: "all")

study_guide

topic: string    — Topic or concept to study (e.g., "quadratic equations")
depth?: string   — "quick", "standard", or "comprehensive" (default: "standard")

Workflows

Topic exploration: list_subjectsget_topic_treeget_courseget_lessonget_content / get_transcript

Quick lookup: searchget_content or get_articleget_transcript (if video)

Study session: search or get_topic_treestudy_guide for review, then get_article / get_transcript for deep dives

Course overview: get_course → pick a unit/lesson → get_lessonget_content

Test prep: get_quiz → review covered lessons → get_exercise for practice → get_transcript / get_article to study weak areas

Development

git clone https://github.com/aicoder2009/khanacademyMCP.git
cd khanacademyMCP
npm install
npm run build

Test with:

echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | node dist/index.js

How It Works

Khan Academy deprecated their public API in 2020. This MCP server uses:

  • Khan Academy's internal GraphQL API — safelisted queries for content metadata and search
  • YouTube transcript API — fetches video captions/subtitles
  • Page scraping — extracts structured data from Khan Academy web pages as a fallback
  • Static catalog — hardcoded top-level subjects for reliable list_subjects

All access is read-only with rate limiting (500ms between requests) and in-memory caching to be respectful of Khan Academy's servers.

Limitations

  • No authentication — cannot access user-specific data (progress, recommendations)
  • Khan Academy's internal API may change without notice — static fallbacks ensure basic functionality
  • Transcript availability depends on YouTube captions being present
  • Rate-limited to avoid overloading Khan Academy's servers

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured