
Knowledge Graph Mcp
This connects Claude to a SQLite knowledge graph designed for tracking student learning with spaced repetition. You get tools to add concepts as nodes, link them with prerequisite or build_on relationships, and update mastery scores across recall, application, and explanation dimensions. When you log review quality (0-5), it runs SM-2 scheduling to calculate next review dates. The query_graph tool surfaces insights like knowledge gaps, concepts due for review, or what's ready to learn next based on prerequisite mastery. You can generate Mermaid visualizations of concept neighborhoods and extract learning paths. Reach for this if you're building tutoring agents that need to maintain persistent models of what students know and when they should review it.
- GitHub stars
- 1
- tools
- 7
- transport
- STDIO
- env var
- 1
- last updated
- Dec 30, 2025
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
add_nodeCreate a new concept node.
Create a new concept node.
No parameter schema in public metadata yet.
add_edgeCreate relationships between concepts.
Create relationships between concepts.
No parameter schema in public metadata yet.
update_nodeUpdate mastery and record reviews. Providing a `quality` rating (0-5) triggers spaced repetition scheduling.
Update mastery and record reviews. Providing a `quality` rating (0-5) triggers spaced repetition scheduling.
No parameter schema in public metadata yet.
query_graphIntelligent queries for learning insights.
Intelligent queries for learning insights.
No parameter schema in public metadata yet.
read_subgraphGet the neighborhood around a concept with Mermaid visualization.
Get the neighborhood around a concept with Mermaid visualization.
No parameter schema in public metadata yet.
get_learning_pathGet ordered prerequisites for a target concept.
Get ordered prerequisites for a target concept.
No parameter schema in public metadata yet.
get_statisticsGet learning progress metrics.
Get learning progress metrics.
No parameter schema in public metadata yet.
Sponsors
Configuration
KNOWLEDGE_GRAPH_DB_PATHCustom path for SQLite database file (optional, defaults to ~/.knowledge_graph/knowledge.db)
Readme
Knowledge Graph MCP Server
An MCP (Model Context Protocol) server for tracking student learning via a knowledge graph. Built with FastMCP, it enables LLMs to build, query, and update a personalized knowledge map with spaced repetition scheduling.
Features
- Knowledge Graph Storage: SQLite-backed graph with concepts as nodes and relationships as edges
- Multi-dimensional Mastery Tracking: Track recall, application, and explanation abilities separately
- Spaced Repetition (SM-2): Automatic scheduling of review sessions based on performance
- Misconception Tracking: Record and query common misconceptions for targeted remediation
- Intelligent Queries: Find knowledge gaps, ready-to-learn concepts, struggling areas
- Mermaid Visualization: Generate visual diagrams of the knowledge graph
Installation
Option 1: Install from Smithery (Recommended)
Install directly via Smithery:
npx @smithery/cli install @zcsabbagh/knowledge-graph-mcp --client claude
Or use the hosted version at: https://smithery.ai/server/@zcsabbagh/knowledge-graph-mcp
Details
- Repository
- github.com/zcsabbagh/knowledge-graph-mcp
- Categories
- AI & LLM Tools, Documents & Knowledge
- Package
knowledge-graph-mcp- Transport
- STDIO
- Registry
- MCP registry, active