SQLite Project Memory MCP
Memoria de Proyecto SQLite MCP
Servidor MCP respaldado por SQLite para almacenar la memoria del proyecto como un núcleo relacional compatible con grafos.
Por qué este proyecto
Mantiene el estado autoritativo en SQLite (fuente única de verdad).
Proporciona semántica de grafos (
entities,relationships,content,tags).Admite lecturas estructuradas (
query_view) y vistas en markdown generadas explícitamente.Diseñado para flujos de trabajo seguros para agentes de IA.
Related MCP server: @contextable/mcp
Modelo central
entitiesattributesrelationshipscontenttagsevents,snapshots,snapshot_entities(auditoría/historial)
Objetivos compatibles con sync-document
Documentos principales:
architecture,decisions,plan,notes,roadmapDocumentos extendidos:
kpi,okr,strategy,risk,issue,epic,story,feature,milestone,release,dependency,objective,initiative,metric,capability,assumption,problem_statement,retrospective,action_item
Instalación
Clona el repositorio en una subcarpeta sqlite-mcp de tu proyecto y luego ejecuta el instalador una vez.
El script detecta su ubicación, coloca todos los archivos de tiempo de ejecución dentro de Project Memory/ y escribe .vscode/mcp.json.
No se requiere instalación de Python. El instalador descarga uv y lo utiliza para obtener
un intérprete CPython 3.12.9 fijado automáticamente. El intérprete se almacena en caché en
Project Memory/.uv/python/ y el entorno virtual se crea en Project Memory/.venv.
Si la descarga de uv falla (por ejemplo, detrás de un firewall), el instalador recurre a cualquier
Python 3.11+ que ya esté en la máquina.
Importante: abre VS Code en la raíz de tu proyecto (la carpeta principal), no en la subcarpeta sqlite-mcp.
La configuración de MCP se escribe en la raíz del proyecto en .vscode/mcp.json.
Windows (PowerShell)
# from your project root
git clone https://github.com/WebRTCGame/SQLITE-MCP.git sqlite-mcp
.\sqlite-mcp\install.ps1Bandera opcional:
-LogFile install.log— guarda una transcripción completa para depuración-AppendInstructions— añade el fragmento al archivo de instrucciones sugerido (idempotente)
Linux / macOS
# from your project root
git clone https://github.com/WebRTCGame/SQLITE-MCP.git sqlite-mcp
chmod +x ./sqlite-mcp/install.sh
./sqlite-mcp/install.shBandera opcional:
--log-file install.log— guarda una transcripción completa para depuración--append-instructions— añade el fragmento al archivo de instrucciones sugerido (idempotente)
Para actualizar: después de una instalación anidada exitosa, los scripts residen bajo Project Memory/ porque el checkout de sqlite-mcp se mueve allí. Vuelve a ejecutar el instalador desde la raíz de tu proyecto con Project Memory\install.ps1 (Windows) o Project Memory/install.sh (Linux/macOS). Para instalaciones in-place/de desarrollador, vuelve a ejecutar el mismo comando.
Solo pip (desarrollador / avanzado)
Se utiliza cuando deseas gestionar el entorno tú mismo (requiere Python 3.11+):
python -m venv .venv
source .venv/bin/activate # or .venv\Scripts\Activate.ps1 on Windows
pip install -e .O con uv directamente (no se necesita Python del sistema — uv descarga Python automáticamente):
uv venv --python 3.12.9 .venv
uv pip install -e .Ejemplo completo:
./sqlite-mcp/install.shIniciar servidor
& ".\Project Memory\.venv\Scripts\python.exe" -m sqlite_mcp_serverRutas
Project Memory/.venv— entorno virtual (Python 3.12.9 fijado)Project Memory/.uv/bin/uv[.exe]— gestor de tiempo de ejecución uv (descargado por el instalador)Project Memory/.uv/python/— intérprete CPython fijado (obtenido por uv en la primera ejecución)Project Memory/pm_data/project_memory.dbProject Memory/pm_exports.vscode/mcp.json.vscode/settings.jsontambién puede ser creado automáticamente por Copilot/VS Code con entradaschat.mcp.serverSamplingparasqlite-project-memory; esto es esperado.
Para anular la versión de Python fijada:
$env:SQLITE_MCP_PYTHON_VERSION = "3.13.0"; .\sqlite-mcp\install.ps1SQLITE_MCP_PYTHON_VERSION=3.13.0 ./sqlite-mcp/install.shHerramientas CLI
sqlite-project-memory-admin bootstrap-self --repo-root .
sqlite-project-memory-admin project-state
sqlite-project-memory-admin health
sqlite-project-memory-admin sync-document architecture --input-path architecture.md
sqlite-project-memory-admin sync-document decisions --input-path decisions.md
sqlite-project-memory-admin sync-document roadmap --input-path roadmap.md
sqlite-project-memory-admin export-views --user-requested --request-reason "User asked for a roadmap export" --require-existing-dir exports todo roadmap architecture
sqlite-project-memory-admin export-views --user-requested --request-reason "User asked for refreshed generated docs" --force todo roadmap architecture
sqlite-project-memory-admin export-json --output-path exports/project_memory.snapshot.json
sqlite-project-memory-admin import-json --input-path exports/project_memory.snapshot.jsonConfiguración
Variables de entorno:
SQLITE_MCP_PROJECT_ROOTSQLITE_MCP_DB_PATHSQLITE_MCP_EXPORT_DIRSQLITE_MCP_TRANSPORT(stdioostreamable-http)SQLITE_MCP_LOG_LEVEL(INFOpor defecto)SQLITE_MCP_LOG_FORMAT(jsonotext)
Hook post-instalación
Crea
.scripts/post_install.ps1(PowerShell) o.scripts/post_install.sh.El script de instalación ejecuta el hook si está presente.
Inicio rápido (Windows)
Clona el repositorio en tu proyecto.
Ejecuta el instalador:
git clone https://github.com/WebRTCGame/SQLITE-MCP.git sqlite-mcp .\sqlite-mcp\install.ps1Después de la instalación, asegúrate de que VS Code esté abierto en la raíz del proyecto principal (por ejemplo
C:\CODE\TestProject), no enC:\CODE\TestProject\sqlite-mcp.Activa el venv de tiempo de ejecución:
& ".\Project Memory\.venv\Scripts\Activate.ps1"Ejecuta la autocomprobación:
sqlite-project-memory-admin --db-path "Project Memory/pm_data/project_memory.db" project-state sqlite-project-memory-admin --db-path "Project Memory/pm_data/project_memory.db" healthInicia el servidor:
python -m sqlite_mcp_server
Inicio rápido (Linux/macOS)
Clona el repositorio en tu proyecto.
Ejecuta el instalador:
git clone https://github.com/WebRTCGame/SQLITE-MCP.git sqlite-mcp chmod +x ./sqlite-mcp/install.sh ./sqlite-mcp/install.shDespués de la instalación, asegúrate de que VS Code esté abierto en la raíz del proyecto principal, no en la subcarpeta
sqlite-mcp.Activa el venv de tiempo de ejecución:
source "Project Memory/.venv/bin/activate"Ejecuta la autocomprobación:
sqlite-project-memory-admin --db-path "Project Memory/pm_data/project_memory.db" project-state sqlite-project-memory-admin --db-path "Project Memory/pm_data/project_memory.db" healthInicia el servidor:
python -m sqlite_mcp_server
Notas
render_markdown_views/export_markdown_viewsrequierenuser_requested=trueyrequest_reason.sync-documentestá anclado (no hay registros de texto libre no estructurado en el estado del roadmap).project_stateyhealthson diagnósticos primarios.
Diseño centrado en IA
Escribe entidades/contenido a través de herramientas MCP.
Genera documentos solo bajo solicitud explícita del usuario.
Añade instrucciones de IA a tu proyecto
Después de ejecutar el instalador, pega el fragmento a continuación en tu archivo de instrucciones de IA
(copilot-instructions.md, AGENTS.md, CLAUDE.md o equivalente).
El instalador también imprime este fragmento en la terminal como recordatorio.
## SQLite Project Memory
This project uses the **`sqlite-project-memory` MCP server** as the single source of truth for all project state.
### Mandatory rules
- **NEVER** create, modify, or delete `.md` files for notes, tasks, decisions, roadmaps, or architecture.
- **ALWAYS** use `sqlite-project-memory` MCP tools to store and retrieve project knowledge.
- `README.md` is the **only** markdown file you may edit directly.
- Files in `Project Memory/pm_exports/` are read-only derived artifacts — never edit them directly.
### Tool usage guide
| Intent | Tool to use |
|--------|-------------|
| Add a task / todo | `create_entity` (entity_type: `task`) |
| Record a decision | `create_entity` (entity_type: `decision`) |
| Document a component | `create_entity` (entity_type: `component`) + `write_content` |
| Add a note to an item | `write_content` or `append_content` |
| Query project state | `query_view`, `list_entities`, `get_entity` |
| Search knowledge | `search_content` |
| Link two items | `add_relationship` or `connect_entities` |
| Export to markdown | `export_markdown_views` with `user_requested: true` — only when explicitly asked |
### First action each session
Before making changes, call `get_project_context` to confirm the database path and project root, then call `get_recent_activity` or `query_view` to orient yourself.Lista de verificación de puertas de uso
Para obtener la mejor fiabilidad, confirma todo lo siguiente:
.vscode/mcp.jsoncontiene el servidorsqlite-project-memory.Se aceptó el aviso de aprobación/confianza de MCP de VS Code para este espacio de trabajo.
El chat está en modo Agente (no en modo chat/edición normal).
El agente
Project Memoryestá disponible en el menú desplegable de agentes.La habilidad
/sqlite-project-memoryestá disponible en los comandos de barra diagonal.Tu archivo de instrucciones del proyecto incluye el fragmento de Memoria de Proyecto SQLite.
Inicia cada sesión con
get_project_contexty luegoget_recent_activityoquery_view.
El instalador imprime un Usage Gates Report con PASS o ACTION REQUIRED para las puertas que puede validar automáticamente.
Si las herramientas aún no aparecen, primero recarga o reinicia completamente VS Code e inicia una nueva sesión de chat de Agente.
Si el servidor no se está ejecutando después del reinicio, ejecuta MCP: Start Server desde la Paleta de Comandos, selecciona sqlite-project-memory y reinicia la sesión de chat.
Available Tools
41 toolsadd_relationshipC
Create a typed graph edge between two entities.
Inputs: relationship_id (required), from_entity (required), to_entity (required), relationship_type (required). Returns: object
append_contentD
Add a piece of content to an entity.
Inputs: entity_id (required), content_type (required), body (required), content_id. Returns: object
apply_performance_tuningC
Tune SQLite settings for throughput during heavy project-memory workloads.
Inputs: journal_mode, synchronous, temp_store, cache_size, +2 more. Returns: object
archive_entityA
Archive an entity without deleting its history or related project memory.
Inputs: entity_id (required), reason, archived_status. Returns: object
bootstrap_project_memoryC
Initialize a project root entity and standard memory-area anchor entities.
Inputs: project_id (required), project_name (required), description, tags. Returns: object
connect_entitiesC
Create a relationship if missing, otherwise return the existing edge.
Inputs: from_entity (required), to_entity (required), relationship_type (required), relationship_id. Returns: object
create_entityC
Create a new authoritative project entity.
Inputs: entity_id (required), entity_type (required), name, description, +3 more. Returns: object
create_snapshotC
Create a named snapshot of current project state.
Inputs: snapshot_id (required), name (required), description, entity_ids. Returns: object
delete_entityA
Delete an entity with guardrails; non-forced deletion requires prior archiving and no critical dependents.
Inputs: entity_id (required), force. Returns: object
delete_relationshipB
Delete a relationship by id and record the removal in project history.
Inputs: relationship_id (required). Returns: object
export_markdown_viewsB
Write generated markdown views only after an explicit user request for a human-readable artifact.
Inputs: view_names, output_dir, overwrite, require_existing_dir, +2 more. Returns: object
find_similar_entitiesB
Find likely duplicate or related entities before creating a new one.
Inputs: name (required), entity_type, limit. Returns: result
get_architecture_summaryB
Return a compact architecture-oriented node and relationship summary.
Inputs: node_limit, relationship_limit, compact. Returns: object
get_database_healthB
Report likely duplicates, low-quality records, and retention pressure in project memory.
Inputs: limit. Returns: object
get_decision_logB
Return decisions and recent supporting note excerpts without requiring ad hoc SQL.
Inputs: limit, offset, compact. Returns: object
get_dependency_viewC
Return dependency-oriented graph data with stable compact fields.
Inputs: root_entity_id, max_depth, relationship_types, limit, +1 more. Returns: object
get_entityC
Fetch an entity and optionally include related metadata, content, and events.
Inputs: entity_id (required), include_related. Returns: object
get_entity_graphC
Traverse outward relationship dependencies from an entity.
Inputs: entity_id (required), max_depth, relationship_type, edge_limit, +2 more. Returns: object
get_or_create_entityB
Reuse an exact entity when it already exists or create one with a generated stable id.
Inputs: entity_type (required), name (required), entity_id, description, +3 more. Returns: object
get_project_contextA
Return the current project root, DB path, and export directory.
Inputs: no named parameters. Returns: object
get_recent_activityC
Return recent entities, content, and events to help an AI resume context quickly.
Inputs: limit, offset, compact. Returns: object
get_recent_reasoningC
Return recent reasoning excerpts for quick AI context recovery.
Inputs: limit, offset, compact. Returns: object
get_snapshotB
Fetch a named snapshot and its captured entities.
Inputs: snapshot_id (required). Returns: object
list_entitiesC
List entities with optional type, status, attribute, tag, and text filters.
Inputs: entity_type, status, attribute_key, attribute_value, +4 more. Returns: result
list_relationshipsC
List graph edges, optionally constrained to an entity and direction.
Inputs: entity_id, relationship_type, direction, limit. Returns: result
list_viewsB
List available view names for query_view discovery.
Inputs: no named parameters. Returns: result
merge_entitiesB
Merge a duplicate source entity into a target entity with deterministic conflict handling.
Inputs: source_entity_id (required), target_entity_id (required), attribute_conflict. Returns: object
prune_content_retentionC
Prune older reasoning/log content while keeping the most recent records per entity and type.
Inputs: content_types, keep_latest, entity_id, dry_run. Returns: object
query_viewB
Query a named SQL view for generic reporting and model projections.
Inputs: view_name (required), params. Returns: object
refresh_task_summaryB
Rebuild a task summary materialized table for faster open task queries.
Inputs: no named parameters. Returns: object
render_markdown_viewsA
Render markdown document views only after an explicit user request for a human-readable artifact.
Inputs: view_names, user_requested, request_reason. Returns: object
resolve_entity_by_nameC
Resolve a human-readable name to an existing entity when possible.
Inputs: name (required), entity_type, limit. Returns: object
run_read_queryC
Run a constrained read-only SQL query for diagnostics, analytics, and ad hoc retrieval.
Inputs: sql (required), parameters, limit. Returns: object
search_contentC
Search narrative content using FTS5 when available.
Inputs: query (required), limit. Returns: result
server_infoB
Return server metadata and schema settings.
Inputs: no named parameters. Returns: object
set_project_rootB
Switch project context (root + db + export path) and reconnect database.
Inputs: project_root (required). Returns: object
set_tagsC
Set or merge tag labels for an entity.
Inputs: entity_id (required), tags (required), replace. Returns: object
update_entityC
Update an existing entity's top-level state.
Inputs: entity_id (required), name, description, status. Returns: object
upsert_attributesB
Create or update flexible metadata for an entity.
Inputs: entity_id (required), attributes (required), replace. Returns: object
upsert_entityC
Create an entity if missing or merge updates into an existing entity.
Inputs: entity_id (required), entity_type (required), name, description, +5 more. Returns: object
write_contentC
Write narrative content in one unified API with append|replace semantics.
Inputs: entity_id (required), mode (required), content (required), content_type (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 41 tools
The tools cover distinct operations like entity management, graph relationships, content handling, and queries, but there is notable overlap in some areas. For example, create_entity, get_or_create_entity, and upsert_entity have overlapping purposes for entity creation, and append_content vs. write_content could cause confusion in content addition. Descriptions help clarify, but agents might misselect between these similar tools.
Most tools follow a consistent verb_noun or verb_adjective_noun pattern (e.g., create_entity, list_entities, get_entity_graph), with clear and descriptive names. There are minor deviations like server_info (noun_verb) and apply_performance_tuning (verb_noun_noun), but overall the naming is predictable and readable across the set.
With 41 tools, the count is excessive for a project memory server, leading to potential cognitive overload and inefficiency. While the domain is broad, many tools could be consolidated or streamlined (e.g., multiple entity creation tools, overlapping content tools), making it feel heavy and less well-scoped than ideal for agent use.
The tool set provides comprehensive coverage for project memory management, including full CRUD operations for entities and relationships, content handling, graph traversal, queries, snapshots, health checks, and context management. There are no obvious gaps; agents can perform all core workflows from initialization to archiving and reporting without dead ends.
Maintenance
Related MCP Connectors
Shared project memory for people and AI agents: documents, ERD, diagrams, boards, design mockups.
Project memory, documentation and controlled secret access for AI coding agents.
The system of record for AI agents — open-source (MIT) database where agents and people share data.
Project memory for coding agents: requirements, decisions, code graph and delivery telemetry.
Related MCP Servers
- AlicenseAqualityDmaintenanceA knowledge graph memory server using SQLite to provide persistent, isolated contexts for organizing information into searchable categories like work and personal projects. It features unique ID-based operations and a token-efficient serialization format designed to optimize interactions with LLMs.11MIT
- AlicenseNot gradedqualityDmaintenanceA persistent AI memory server that enables storage and retrieval of context and project artifacts across conversations. It features full-text search, version history, and automatic content chunking using local SQLite or hosted cloud storage.13 npmApache 2.0
- AlicenseNot gradedqualityDmaintenanceA persistent memory server for AI agents that stores structured notes in a local SQLite database with full-text search and graph-based relationships. It features 32 specialized tools for managing long-term context, including version history, automated TTL expiration, and complex filtering.12 npmMIT
- AlicenseNot gradedqualityDmaintenanceA database-backed MCP server that acts as a project memory bank, enabling AI assistants to store, retrieve, and search structured context like decisions, tasks, and architecture using SQLite and vector embeddings.Apache 2.0