Knowledge Graph Memory Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORY_FILE_PATH | No | Path to the memory storage JSONL file (default: memory.jsonl in the server directory) | memory.jsonl |
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
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_entitiesA | Create multiple new entities in the knowledge graph. An entity whose name already exists, or repeats an earlier entity in the same call, is skipped and its observations are not added; the result lists the skipped names in |
| create_relationsB | Create multiple new relations between entities in the knowledge graph. Relations should be in active voice |
| add_observationsB | Add new observations to existing entities in the knowledge graph |
| delete_entitiesA | Delete multiple entities and their associated relations from the knowledge graph |
| delete_observationsC | Delete specific observations from entities in the knowledge graph |
| delete_relationsC | Delete multiple relations from the knowledge graph |
| read_graphA | Read the entire knowledge graph |
| search_nodesC | Search for nodes in the knowledge graph based on a query |
| open_nodesB | Open specific nodes in the knowledge graph by their names |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| knowledge-graph | The full knowledge graph with all entities and relations |
TDQS
Scored across 9 tools
Each tool targets a distinct operation on a distinct object type (entities, relations, observations), and descriptions actively disambiguate (create_entities points to add_observations for existing entities). The only mild overlap is among the retrieval trio read_graph/search_nodes/open_nodes, though their query-vs-names-vs-full-graph semantics differ.
Names consistently use snake_case verb_noun form (create_entities, delete_relations, search_nodes, open_nodes). The only minor deviation is mixing 'create_' for entities/relations with 'add_' for observations, which is a small vocabulary inconsistency rather than a structural one.
Nine tools is well-scoped for a knowledge graph memory server, covering create/read/delete/search across the three graph primitives without redundancy. Each tool earns its place.
The surface covers creation, retrieval, deletion, and search for entities, relations, and observations. The main gap is the absence of true update operations (e.g. renaming an entity or editing an observation), which is only partially mitigated by delete-and-recreate or add_observations.