"Dgraph" matching MCP servers:

Enables LLMs to break down reasoning into an explicit, editable graph of thinking steps, with visualizations and the ability to revise individual steps.

Provides AI coding agents with a local knowledge-graph memory, enabling cross-project retrieval via PageRank diffusion and tools to retrieve, write, extract, update, and view recent knowledge over MCP.

Maps Salesforce metadata into a Neo4j graph database, enabling AI agents to reason about schema and generate accurate SOQL queries.

Enables sophisticated reasoning workflows using graph-based representations for AI models.

Long-term memory system for AI agents that accumulates domain expertise through mentorship, automatically recalls relevant knowledge, and supports memory decay and growth with anti-fabrication.

Enables ingesting documents or text to extract entities and relationships via LLM, storing them in Neo4j, and searching or retrieving episodes.

Enables graph-based fraud propagation scoring for clinical diagnostics, diffusing risk across entities with a deterministic fallback when the ML model is unavailable.