Knowledge Graph MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/zcsabbagh-knowledge-graph-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

4 read · 3 write · 0 delete

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Python package

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• add_edge

  Create a relationship between two concepts in the knowledge graph. Args: source_concept: Source node ID or concept name target_concept: Target node ID or concept name relation_type: Type of relationship. One of: - "prerequisite": Source must be learned before target - "builds_on": Target extends/deepens source concept - "related_to": Concepts are connected (bidirectional semantically) - "contradicts": Common misconception (source is wrong belief about target) - "applies_to": Source concept applies to target domain/topic - "parent_of"…

• add_node

  Create a new concept node in the knowledge graph. Args: concept: Human-readable name for the concept (e.g., "Quadratic Formula") description: Detailed description of what this concept represents domain: Category/domain (e.g., "mathematics", "physics", "programming") difficulty: Estimated cognitive load from 0.0 (easy) to 1.0 (hard). Default 0.5. tags: List of categorization tags (e.g., ["algebra", "equations"]) node_id: Custom ID for the node. Auto-generated from concept if not provided. Returns: Created node object with all fields including initial mastery (0.0) …

• get_learning_path

  Get the ordered learning path to reach a target concept. Returns a topologically sorted list of prerequisites, highlighting which concepts the student still needs to learn (gaps). Args: target_concept: The goal concept to learn (node ID or concept name) include_mastered: Whether to include already-mastered concepts in the path Returns: Ordered path with gap analysis and Mermaid visualization Example: # What do I need to learn before calculus? get_learning_path(target_concept="calculus")

• get_statistics

  Get summary statistics for learning progress. Args: domain: Filter statistics by domain (e.g., "mathematics"). If None, returns all. Returns: Statistics including: - total_concepts: Number of concepts in the graph - mastery_distribution: Counts by mastery level - average_mastery_by_domain: Average mastery per domain - overall_mastery: Overall average mastery - concepts_due_for_review: Count of concepts needing review - misconceptions_count: Count of concepts with misconceptions - struggling_concepts: Top 5 concepts with high difficulty and low mastery Exa…

• query_graph

  Query the knowledge graph for learning insights. Args: query_type: Type of query to execute. One of: - "prerequisites": All prerequisites for a concept (requires node_id) - "ready_to_learn": Concepts where all prerequisites are mastered - "due_for_review": Nodes where scheduled review date has passed - "struggling": High difficulty + low mastery concepts - "stalled": Multiple reviews but mastery not improving - "misconceptions": Nodes with detected misconceptions - "knowledge_gaps": Low mastery nodes blocking other concepts -…

• read_subgraph

  Get the neighborhood around a concept for context. Args: center_node: Node ID or concept name to center on depth: How many edge hops to traverse (1=direct connections, 2=neighbors of neighbors) direction: Which edges to follow: - "upstream": Follow edges where center is target (prerequisites) - "downstream": Follow edges where center is source (what it unlocks) - "both": Follow edges in both directions include_mastery: Whether to include mastery data in response output_format: Output format: - "json": Just the structured data - "merm…

• update_node

  Update a node's properties and record a review session. Args: node_id: ID or concept name of the node to update mastery_level: Overall mastery (0.0-1.0). Overrides dimensional calculation. mastery_recall: Ability to retrieve from memory (0.0-1.0) mastery_application: Ability to use in new contexts (0.0-1.0) mastery_explanation: Ability to teach/explain to others (0.0-1.0) quality: SM-2 review quality rating (0-5). Triggers spaced repetition scheduling. - 5: Perfect response - 4: Correct after hesitation - 3: Correct with serious difficulty …

Signals

Stars

1

Forks

0

Open issues

0

Weekly downloads

27

Last commit

Dec 30, 2025 (10 months ago)

Last release

Dec 30, 2025 (10 months ago)

Last package publish

Dec 30, 2025 (10 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.zcsabbagh/knowledge-graph-mcp

Version

0.1.0

Auth

No auth

Packages

pypi knowledge-graph-mcp

License

MIT

Repository

github.com/zcsabbagh/knowledge-graph-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql