VeritasGraph
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| veritasgraph_ingest_documentA | Ingest a document into the VeritasGraph knowledge graph. Chunks the text, extracts entities and relationships with a local model, and records the source chunk behind every node/edge for verifiable attribution. |
| veritasgraph_queryA | Ask a question and get a graph-grounded, multi-hop answer with verifiable [doc#chunk] citations and the reasoning path used. |
| veritasgraph_search_entitiesA | Retrieve the subgraph most relevant to a query (entities, relationships, seeds) without invoking the LLM. Fast graph lookup. |
| veritasgraph_get_graphA | Return the full knowledge graph: all nodes, edges, and stats. |
| veritasgraph_clear_graphA | Clear the entire knowledge graph (destructive; removes all data). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| VeritasGraph knowledge graph | Live snapshot of the local knowledge graph (nodes, edges, stats). |
| VeritasGraph statistics | Counts of entities, relationships, and source chunks. |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: clearing the graph, retrieving the full graph, ingesting documents, querying with reasoning, and searching entities. No ambiguity or overlap.
All tools use the 'veritasgraph_' prefix and mostly follow a verb_noun pattern (e.g., clear_graph, get_graph, ingest_document, search_entities). 'query' deviates slightly as a single verb, but it's still clear and consistent in style.
With 5 tools, the set is well-scoped for a knowledge graph server, covering ingestion, retrieval, searching, and clearing without being excessive or insufficient.
The tool set covers core operations: create (ingest), read (get_graph, search_entities, query), and delete (clear_graph). Minor gaps include the lack of update or individual entity deletion, but these are reasonable omissions for the intended use case.