MCP DuckDB Knowledge Graph Memory Server
Servidor de memoria de gráficos de conocimiento MCP DuckDB
Una versión bifurcada del servidor de memoria oficial Knowledge Graph .
Instalación
Instalación mediante herrería
Para instalar DuckDB Knowledge Graph Memory Server para Claude Desktop automáticamente a través de Smithery :
npx -y @smithery/cli install @IzumiSy/mcp-duckdb-memory-server --client claudeInstalación manual
De lo contrario, agregue @IzumiSy/mcp-duckdb-memory-server en su claude_desktop_config.json manualmente ( MEMORY_FILE_PATH es opcional)
{
"mcpServers": {
"graph-memory": {
"command": "npx",
"args": [
"-y",
"@izumisy/mcp-duckdb-memory-server"
],
"env": {
"MEMORY_FILE_PATH": "/path/to/your/memory.data"
}
}
}
}Los datos almacenados en esa ruta son un archivo de base de datos DuckDB.
Estibador
Construir
docker build -t mcp-duckdb-graph-memory .Correr
docker run -dit mcp-duckdb-graph-memoryRelated MCP server: Knowledge Graph Memory Server
Uso
Utilice la instrucción de ejemplo a continuación
Follow these steps for each interaction:
1. User Identification:
- You should assume that you are interacting with default_user
- If you have not identified default_user, proactively try to do so.
2. Memory Retrieval:
- Always begin your chat by saying only "Remembering..." and search relevant information from your knowledge graph
- Create a search query from user words, and search things from "memory". If nothing matches, try to break down words in the query at first ("A B" to "A" and "B" for example).
- Always refer to your knowledge graph as your "memory"
3. Memory
- While conversing with the user, be attentive to any new information that falls into these categories:
a) Basic Identity (age, gender, location, job title, education level, etc.)
b) Behaviors (interests, habits, etc.)
c) Preferences (communication style, preferred language, etc.)
d) Goals (goals, targets, aspirations, etc.)
e) Relationships (personal and professional relationships up to 3 degrees of separation)
4. Memory Update:
- If any new information was gathered during the interaction, update your memory as follows:
a) Create entities for recurring organizations, people, and significant events
b) Connect them to the current entities using relations
b) Store facts about them as observationsMotivación
Este proyecto mejora el servidor de memoria MCP Knowledge Graph original reemplazando su backend con DuckDB.
¿Por qué DuckDB?
El servidor de memoria original de Knowledge Graph de MCP utilizaba un archivo JSON como almacén de datos y realizaba búsquedas en memoria. Si bien este enfoque funciona bien con conjuntos de datos pequeños, presenta varios desafíos:
Rendimiento : el rendimiento de la búsqueda en memoria se degrada a medida que crece el conjunto de datos
Escalabilidad : el uso de memoria aumenta significativamente cuando se manejan grandes cantidades de entidades y relaciones.
Flexibilidad de consultas : las consultas complejas y las búsquedas condicionales son difíciles de implementar
Integridad de los datos : garantizar la atomicidad de las transacciones y las operaciones CRUD es un desafío
Se eligió DuckDB para abordar estos desafíos:
Procesamiento rápido de consultas : DuckDB está optimizado para consultas analíticas y funciona bien incluso con grandes conjuntos de datos
Interfaz SQL : se puede utilizar SQL estándar para ejecutar consultas complejas fácilmente
Soporte de transacciones : admite el procesamiento de transacciones para mantener la integridad de los datos
Capacidades de indexación : permite la creación de índices para mejorar el rendimiento de la búsqueda.
Base de datos integrada : funciona dentro de la aplicación sin necesidad de un servidor de base de datos externo
Detalles de implementación
Esta implementación utiliza DuckDB como sistema de almacenamiento backend, centrándose en dos aspectos clave:
Estructura de la base de datos
El gráfico de conocimiento se almacena en una estructura de base de datos relacional como se muestra a continuación:
erDiagram
ENTITIES {
string name PK
string entityType
}
OBSERVATIONS {
string entityName FK
string content
}
RELATIONS {
string from_entity FK
string to_entity FK
string relationType
}
ENTITIES ||--o{ OBSERVATIONS : "has"
ENTITIES ||--o{ RELATIONS : "from"
ENTITIES ||--o{ RELATIONS : "to"Este diseño de esquema permite el almacenamiento y la recuperación eficientes de los componentes del gráfico de conocimiento manteniendo al mismo tiempo las relaciones entre entidades, observaciones y relaciones.
Implementación de búsqueda difusa
La implementación combina consultas SQL con Fuse.js para una búsqueda flexible de entidades:
Las consultas SQL de DuckDB recuperan los datos base de la base de datos
Fuse.js proporciona capacidades de coincidencia difusa sobre los datos recuperados
Este enfoque híbrido permite tanto consultas estructuradas como coincidencias de texto flexibles.
Los resultados de la búsqueda incluyen coincidencias exactas y parciales, clasificadas por relevancia.
Desarrollo
Configuración
pnpm installPruebas
pnpm testLicencia
Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.
Available Tools
8 toolsadd_observationsC
Add new observations to existing entities in the knowledge graph
Inputs: observations (required).
create_entitiesC
Create multiple new entities in the knowledge graph
Inputs: entities (required).
create_relationsC
Create multiple new relations between entities in the knowledge graph. Relations should be in active voice
Inputs: relations (required).
delete_entitiesC
Delete multiple entities and their associated relations from the knowledge graph
Inputs: entityNames (required).
delete_observationsC
Delete specific observations from entities in the knowledge graph
Inputs: deletions (required).
delete_relationsC
Delete multiple relations from the knowledge graph
Inputs: relations (required).
open_nodesC
Open specific nodes in the knowledge graph by their names
Inputs: names (required).
search_nodesC
Search for nodes in the knowledge graph based on a query
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Most tools have distinct purposes targeting different aspects of the knowledge graph (entities, relations, observations, nodes), though 'open_nodes' and 'search_nodes' could potentially overlap in functionality if opening involves searching. The descriptions clarify that 'open_nodes' accesses specific named nodes while 'search_nodes' performs query-based lookup, but agents might still confuse them in some scenarios.
All tools follow a consistent verb_noun pattern with snake_case naming (e.g., add_observations, create_entities, delete_relations). The verbs are clear and appropriate for the actions (add, create, delete, open, search), and there are no deviations in style or convention throughout the set.
With 8 tools, this server is well-scoped for a knowledge graph memory system. Each tool appears to serve a specific and necessary function for managing entities, relations, observations, and nodes, without being overly sparse or bloated. The count aligns well with the domain's typical CRUD and query operations.
The tool set provides strong coverage for core knowledge graph operations, including creation, deletion, and querying of entities, relations, and observations. A minor gap is the lack of update tools (e.g., update_entities or update_relations), which might require workarounds like delete-and-recreate, but the surface is otherwise comprehensive for the stated purpose.
Maintenance
Related MCP Connectors
Persistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.
Memory for Claude, ChatGPT and other AI apps: notes and docs as a searchable graph, EU-hosted.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Persistent memory and knowledge graph for AI assistants — keyword + vector + graph search.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.10887MIT
- AlicenseBqualityFmaintenanceA persistent memory implementation using a local knowledge graph that lets Claude remember information about users across conversations.96MIT
- AlicenseNot gradedqualityDmaintenanceA persistent memory system using a local knowledge graph that enables Claude to remember information about users across chats, with advanced search, graph traversal, and filtering capabilities for entities, relations, and observations.MIT
- AlicenseNot gradedqualityDmaintenanceA persistent memory server for Claude Code that captures session context and tool outputs to inject relevant history into future sessions. It enables long-term recall through semantic search and automatic context management, allowing for more consistent and context-aware coding interactions.253AGPL 3.0