Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by edobez • Data & Databases
A local MCP server that provides persistent memory using a file-backed knowledge graph to store entities, observations, and relations for conversational agents.
Persistently store user profiles, preferences, and short facts across conversations using a local JSON-backed knowledge graph.
Search and retrieve contextual memories by querying entity names, types, or observation text to inform responses.
Model and traverse relationships between entities (people, organizations, events) to maintain context and connections across sessions.
This server implements a persistent, local knowledge-graph-based memory store (entities, relations, observations) for use with MCP-compatible agents. It supports creating, reading, searching, and deleting entities, relations, and observations, with a JSON file backend and simple API tools. The project is a Python port of the original reference MCP memory server and is distributed under the MIT License, making it easy to self-host and integrate for chat personalization and stateful agents.
Create multiple new entities in the knowledge graph. Args: entities: List of entities to create, each with name, type and observations Returns: List of newly created entities (excluding any that already existed)
Create new relations between entities in the knowledge graph. Args: relations: List of relations to create, each with from_, to and relationType Returns: List of newly created relations (excluding any duplicates)
Add new observations to existing entities. Args: observations: List of observations to add, each with entityName and contents Returns: List of results showing which observations were added to which entities
Delete entities and their associated relations from the graph. Args: entity_names: List of entity names to delete
Delete specific observations from entities. Args: deletions: List of deletions, each with entityName and observations to remove
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.