Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEMORY_FILENoSpecifies the path to the JSON file used for storing the knowledge graph data. (Default: dist/data/memory.json)dist/data/memory.json
SCHEMAS_DIRNoPath to schema files directory. (Default: dist/data/schemas/memory.json)dist/data/schemas/memory.json

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

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
add_nodesC

Add multiple new nodes in the knowledge graph

update_nodesA

Update existing nodes in the knowledge graph: rename them, change their type, or replace their metadata. Only the fields you pass are changed

add_edgesB

Add multiple new edges between nodes in the knowledge graph. Edges should be in active voice

update_edgesC

Update existing edges in the knowledge graph

delete_nodesA

Delete multiple nodes and their associated edges from the knowledge graph

delete_edgesC

Delete multiple edges from the knowledge graph

read_graphA

Read the entire knowledge graph. On a large graph, prefer search_nodes or open_nodes to fetch only what is needed

search_nodesA

Search for nodes in the knowledge graph. Returns the nodes that contain every word of the query in their name, type or metadata, plus their direct neighbours

open_nodesC

Open specific nodes in the knowledge graph by their names

add_metadataB

Add new metadata to existing nodes in the knowledge graph

delete_metadataC

Delete specific metadata from nodes in the knowledge graph

add_locationB

Add a new location (a city, building, room, region...) to the knowledge graph

update_locationC

Update an existing location in the knowledge graph

delete_locationC

Delete an existing location from the knowledge graph

add_npcC

Add a new character (NPC) to the knowledge graph

update_npcC

Update an existing npc in the knowledge graph

delete_npcC

Delete an existing npc from the knowledge graph

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.2/5.0

Scored across 17 tools

Disambiguation3/5

Most tools target distinct resources, but the generic node tools overlap with the typed entity tools: add_nodes/update_nodes/delete_nodes can create or remove anything add_location, add_npc, add_edges evidently cover, and metadata can be replaced via update_nodes or mutated via add_metadata/delete_metadata. read_graph vs search_nodes vs open_nodes are reasonably distinct thanks to explicit guidance. The agent can mostly cope, but the node-vs-entity boundary is genuinely blurry.

Naming Consistency4/5

Nearly everything follows a clean verb_noun snake_case pattern (add_edges, update_location, delete_npc). Minor deviations: nouns are plural for nodes/edges but singular for npc, and read_graph/search_nodes/open_nodes mix verb styles (read/search/open) for the same read family. Still highly predictable overall.

Tool Count4/5

17 tools is slightly above the sweet spot but each earns a place given five resource families (nodes, edges, metadata, locations, NPCs) that each need create/update/delete. Nothing feels redundant enough to cut, though the typed-entity triples inflate the count.

Completeness4/5

Core lifecycle coverage exists for nodes (add/update/delete/read/search), edges (add/update/delete), metadata (add/delete), locations and NPCs (add/update/delete). Gaps are minor: no update_metadata convenience, no way to list or search edges independently, and no bulk-clear/graph-delete operation. Agents can work around these via read_graph and update_nodes metadata replacement.

Maintenance

ActivityMaintained
ResponsivenessLimited data