Memento
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORY_DB_PATH | Yes | Path to the SQLite database file used for storing memory | |
| SQLITE_VEC_PATH | No | Optional full path to vec0.dylib if automatic detection fails |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_entitiesA | Create entities in the knowledge graph. Inserts each entity if not exists and optionally seeds it with observations. |
| create_relationsB | Create directed relations between entities. Skips existing relations. |
| add_observationsB | Add text observations to existing entities and index them for full-text and semantic search. |
| delete_entitiesB | Delete entities (and cascaded observations/relations) by their names. |
| delete_relationsA | Remove specified relations between entities without deleting the entities themselves. |
| delete_observationsB | Remove specific observations from entities by matching text. |
| read_graphA | Retrieve the entire knowledge graph: all entities with their observations and relations. |
| search_nodesC | Search for entities and relations by semantic similarity. |
| open_nodesA | Expand specified entities: return their full details including observations and relations. |
| set_importanceB | Set the importance level for an entity (critical, important, normal, temporary, deprecated). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool targets a distinct operation: create entities, relations, and observations; read via open_nodes, read_graph, and search_nodes; update via add_observations and set_importance; delete for entities, observations, and relations. No overlap exists.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_entities, delete_observations, search_nodes). No deviations or mixed styles.
10 tools is well-scoped for a knowledge graph management server, covering all essential operations without redundancy. The number is within the ideal range (3-15).
The toolset covers CRUD for entities, observations, and relations, plus search and importance setting. Minor gaps exist: no update for entity properties (beyond importance) and no update for relations, but core workflows are complete.