Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Enable debug mode | true |
| NEO4J_URI | Yes | Neo4j server URI | bolt://127.0.0.1:7687 |
| NEO4J_DATABASE | No | Neo4j database name | neo4j |
| NEO4J_PASSWORD | Yes | Neo4j password | memento_password |
| NEO4J_USERNAME | Yes | Neo4j username | neo4j |
| OPENAI_API_KEY | Yes | OpenAI API key for embeddings | |
| NEO4J_VECTOR_INDEX | No | Vector index name for Neo4j | entity_embeddings |
| MEMORY_STORAGE_TYPE | No | Type of storage backend to use | neo4j |
| OPENAI_EMBEDDING_MODEL | No | OpenAI embedding model to use | text-embedding-3-small |
| NEO4J_VECTOR_DIMENSIONS | No | Vector dimensions for embeddings | 1536 |
| NEO4J_SIMILARITY_FUNCTION | No | Similarity function (cosine|euclidean) | cosine |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_entities | Create multiple new entities in your Memento MCP knowledge graph memory system |
| create_relations | Create multiple new relations between entities in your Memento MCP knowledge graph memory. Relations should be in active voice |
| add_observations | Add new observations to existing entities in your Memento MCP knowledge graph memory |
| delete_entities | Delete multiple entities and their associated relations from your Memento MCP knowledge graph memory |
| delete_observations | Delete specific observations from entities in your Memento MCP knowledge graph memory |
| delete_relations | Delete multiple relations from your Memento MCP knowledge graph memory |
| get_relation | Get a specific relation with its enhanced properties from your Memento MCP knowledge graph memory |
| update_relation | Update an existing relation with enhanced properties in your Memento MCP knowledge graph memory |
| read_graph | Read the entire Memento MCP knowledge graph memory system |
| search_nodes | Search for nodes in your Memento MCP knowledge graph memory based on a query |
| open_nodes | Open specific nodes in your Memento MCP knowledge graph memory by their names |
| semantic_search | Search for entities semantically using vector embeddings and similarity in your Memento MCP knowledge graph memory |
| get_entity_embedding | Get the vector embedding for a specific entity from your Memento MCP knowledge graph memory |
| get_entity_history | Get the version history of an entity from your Memento MCP knowledge graph memory |
| get_relation_history | Get the version history of a relation from your Memento MCP knowledge graph memory |
| get_graph_at_time | Get your Memento MCP knowledge graph memory as it existed at a specific point in time |
| get_decayed_graph | Get your Memento MCP knowledge graph memory with confidence values decayed based on time |
| force_generate_embedding | Forcibly generate and store an embedding for an entity in your Memento MCP knowledge graph memory |
| debug_embedding_config | Debug tool to check embedding configuration and status of your Memento MCP knowledge graph memory system |
| diagnose_vector_search | Diagnostic tool to directly query Neo4j database for entity embeddings, bypassing application abstractions |