neo4j-cypher

The neo4j-cypher skill provides specialized expertise for interacting with Neo4j graph databases through the Model Context Protocol (MCP). It is designed for developers, data engineers, and architects who need to perform complex graph operations, schema design, and query optimization without the overhead of manual connection management. This skill bridges the gap between natural language intent and precise Cypher query syntax, ensuring that graph-based data models are queried and maintained with maximum structural integrity.

• Streamlines the execution of Cypher queries using mcp__neo4j__execute_query while enforcing parameter-based inputs to prevent injection and performance issues.

• Enables automated schema introspection via mcp__neo4j__get_schema, allowing agents to understand node labels, relationship types, property keys, and existing constraints before taking action.

• Supports advanced data modeling workflows, including the creation and verification of indexes, unique constraints, and existence constraints to ensure graph data quality.

• Facilitates graph exploration through path finding queries, variable-length relationship traversal, and complex aggregations common in social network analysis, recommendation systems, and knowledge graph management.

• Integrates with additional MCP servers such as mcp-neo4j-modeler for visualization and validation, and mcp-neo4j-aura for cloud instance lifecycle management.

• Always trigger schema discovery (mcp__neo4j__get_schema) as the first step in any interaction to ensure queries align with the current database state.

• Utilize the provided patterns for MERGE operations (idempotent writes), path queries (shortestPath), and aggregations (count, collect, sum) to maintain high code quality.

• Strictly adhere to best practices: use query parameters instead of string interpolation, validate labels against the schema before writing, and verify index presence to avoid slow graph scans.

• When encountering complex data, decompose tasks into independent units: schema retrieval, query formulation, execution, and validation.

• The input is typically natural language request or a technical specification, while the output expected is valid Cypher syntax or JSON-formatted graph results returned by the MCP tools.