diagnose_vector_search

MCP tool from Memento MCP by gannonh

Information about the Neo4j vector index, embedding counts, and search functionality

How to use it

diagnose_vector_search is exposed by the Memento MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the diagnose_vector_search tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Memento MCP

$npx -y @smithery/cli install @gannonh/memento-mcp --client claude

FULL MEMENTO MCP LISTING

Other tools in Memento MCP (39)

add_observations

(number, optional): Confidence level (0.0-1.0)

(string[]): New observations to add

create_entities

create_relations

debug_embedding_config

Information about the current embedding service configuration

(number): Optional decay factor override

delete_entities

delete_observations

delete_relations

(string): The name of the entity to get the embedding for

(string[], optional): Filter results by entity types

(string): Target entity

(string): Type classification

force_generate_embedding

Forces the generation of an embedding for a specific entity

(string): Source entity name

get_decayed_graph

get_entity_embedding

get_entity_history

get_graph_at_time

get_relation_history

(boolean, optional): Combine keyword and semantic search (default: true)

(number, optional): Maximum results to return (default: 10)

(object, optional): Custom metadata fields

(number, optional): Minimum similarity threshold (0.0-1.0, default: 0.6)

(string): Entity identifier

(string[]): Associated observations

(string): The text query to search for semantically

(number): Reference timestamp for decay calculation (milliseconds since epoch)

(string): Relationship type

semantic_search

semantic_weight

(number, optional): Weight of semantic results in hybrid search (0.0-1.0, default: 0.6)

(number, optional): Relation strength (0.0-1.0)

(string): Target entity name

update_relation