Skip to main content
Glama
SQLite Project Memory MCP

SQLite Project Memory MCP

by WebRTCGame

SQLite Project Memory MCP

SQLite-basierter MCP-Server zum Speichern von Projektgedächtnis als graph-freundlicher relationaler Kern.

Warum dieses Projekt

  • Hält den maßgeblichen Zustand in SQLite (Single Source of Truth).

  • Bietet Graph-Semantik (entities, relationships, content, tags).

  • Unterstützt strukturierte Lesevorgänge (query_view) und explizit generierte Markdown-Ansichten.

  • Entwickelt für KI-Agenten-sichere Workflows.

Related MCP server: @contextable/mcp

Kernmodell

  • entities

  • attributes

  • relationships

  • content

  • tags

  • events, snapshots, snapshot_entities (Audit/Historie)

Unterstützte sync-document-Ziele

  • Kerndokumente: architecture, decisions, plan, notes, roadmap

  • Erweiterte Dokumente: kpi, okr, strategy, risk, issue, epic, story, feature, milestone, release, dependency, objective, initiative, metric, capability, assumption, problem_statement, retrospective, action_item

Installation

Klonen Sie das Repo in einen sqlite-mcp-Unterordner Ihres Projekts und führen Sie dann einmalig das Installationsprogramm aus. Das Skript erkennt seinen Speicherort, platziert alle Laufzeitdateien in Project Memory/ und schreibt .vscode/mcp.json.

Keine Python-Installation erforderlich. Das Installationsprogramm lädt uv herunter und verwendet es, um automatisch einen fixierten CPython 3.12.9-Interpreter abzurufen. Der Interpreter wird in Project Memory/.uv/python/ zwischengespeichert und die virtuelle Umgebung wird in Project Memory/.venv erstellt. Wenn der uv-Download fehlschlägt (z. B. hinter einer Firewall), greift das Installationsprogramm auf ein bereits auf dem Computer vorhandenes Python 3.11+ zurück.

Wichtig: Öffnen Sie VS Code in Ihrem Projektstammverzeichnis (dem übergeordneten Ordner), nicht im sqlite-mcp-Unterordner. Die MCP-Konfiguration wird in das Projektstammverzeichnis unter .vscode/mcp.json geschrieben.

Windows (PowerShell)

# from your project root
git clone https://github.com/WebRTCGame/SQLITE-MCP.git sqlite-mcp
.\sqlite-mcp\install.ps1

Optionale Flags:

  • -LogFile install.log — speichert ein vollständiges Transkript für das Debugging

  • -AppendInstructions — hängt den Schnipsel an die vorgeschlagene Anweisungsdatei an (idempotent)

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.sh

Optionale Flags:

  • --log-file install.log — speichert ein vollständiges Transkript für das Debugging

  • --append-instructions — hängt den Schnipsel an die vorgeschlagene Anweisungsdatei an (idempotent)

Zum Aktualisieren: Nach einer erfolgreichen verschachtelten Installation befinden sich die Skripte unter Project Memory/, da der sqlite-mcp-Checkout dorthin verschoben wurde. Führen Sie das Installationsprogramm erneut von Ihrem Projektstammverzeichnis aus mit Project Memory\install.ps1 (Windows) oder Project Memory/install.sh (Linux/macOS). Für In-Place-/Entwicklerinstallationen führen Sie denselben Befehl erneut aus.

Nur pip (Entwickler / Fortgeschrittene)

Wird verwendet, wenn Sie die Umgebung selbst verwalten möchten (erfordert Python 3.11+):

python -m venv .venv
source .venv/bin/activate   # or .venv\Scripts\Activate.ps1 on Windows
pip install -e .

Oder direkt mit uv (kein System-Python erforderlich — uv lädt Python automatisch herunter):

uv venv --python 3.12.9 .venv
uv pip install -e .

Vollständiges Beispiel:

./sqlite-mcp/install.sh

Server starten

& ".\Project Memory\.venv\Scripts\python.exe" -m sqlite_mcp_server

Pfade

  • Project Memory/.venv — virtuelle Umgebung (fixiertes Python 3.12.9)

  • Project Memory/.uv/bin/uv[.exe] — uv-Laufzeitmanager (vom Installationsprogramm heruntergeladen)

  • Project Memory/.uv/python/ — fixierter CPython-Interpreter (wird beim ersten Ausführen von uv abgerufen)

  • Project Memory/pm_data/project_memory.db

  • Project Memory/pm_exports

  • .vscode/mcp.json

  • .vscode/settings.json kann ebenfalls automatisch von Copilot/VS Code mit chat.mcp.serverSampling-Einträgen für sqlite-project-memory erstellt werden; dies ist zu erwarten.

Um die fixierte Python-Version zu überschreiben:

$env:SQLITE_MCP_PYTHON_VERSION = "3.13.0"; .\sqlite-mcp\install.ps1
SQLITE_MCP_PYTHON_VERSION=3.13.0 ./sqlite-mcp/install.sh

CLI-Tools

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.json

Konfiguration

Umgebungsvariablen:

  • SQLITE_MCP_PROJECT_ROOT

  • SQLITE_MCP_DB_PATH

  • SQLITE_MCP_EXPORT_DIR

  • SQLITE_MCP_TRANSPORT (stdio oder streamable-http)

  • SQLITE_MCP_LOG_LEVEL (INFO Standard)

  • SQLITE_MCP_LOG_FORMAT (json oder text)

Post-Install-Hook

  • Erstellen Sie .scripts/post_install.ps1 (PowerShell) oder .scripts/post_install.sh.

  • Das Installationsskript führt den Hook aus, falls vorhanden.

Schnellstart (Windows)

  1. Klonen Sie das Repo in Ihr Projekt.

  2. Führen Sie das Installationsprogramm aus:

    git clone https://github.com/WebRTCGame/SQLITE-MCP.git sqlite-mcp
    .\sqlite-mcp\install.ps1

    Stellen Sie nach der Installation sicher, dass VS Code im übergeordneten Projektstammverzeichnis geöffnet ist (zum Beispiel C:\CODE\TestProject), nicht in C:\CODE\TestProject\sqlite-mcp.

  3. Aktivieren Sie die Laufzeit-Venv:

    & ".\Project Memory\.venv\Scripts\Activate.ps1"
  4. Führen Sie die Selbstprüfung aus:

    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" health
  5. Starten Sie den Server:

    python -m sqlite_mcp_server

Schnellstart (Linux/macOS)

  1. Klonen Sie das Repo in Ihr Projekt.

  2. Führen Sie das Installationsprogramm aus:

    git clone https://github.com/WebRTCGame/SQLITE-MCP.git sqlite-mcp
    chmod +x ./sqlite-mcp/install.sh
    ./sqlite-mcp/install.sh

    Stellen Sie nach der Installation sicher, dass VS Code im übergeordneten Projektstammverzeichnis geöffnet ist, nicht im sqlite-mcp-Unterordner.

  3. Aktivieren Sie die Laufzeit-Venv:

    source "Project Memory/.venv/bin/activate"
  4. Führen Sie die Selbstprüfung aus:

    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" health
  5. Starten Sie den Server:

    python -m sqlite_mcp_server

Hinweise

  • render_markdown_views/export_markdown_views erfordern user_requested=true und request_reason.

  • sync-document ist verankert (kein unstrukturierter Freitext-Datensatz im Roadmap-Zustand).

  • project_state und health sind primäre Diagnosen.

KI-First-Design

  • Schreiben Sie Entitäten/Inhalte über MCP-Tools.

  • Generieren Sie Dokumente nur auf explizite Benutzeranfrage.

KI-Anweisungen zu Ihrem Projekt hinzufügen

Fügen Sie nach dem Ausführen des Installationsprogramms den unten stehenden Schnipsel in Ihre KI-Anweisungsdatei ein (copilot-instructions.md, AGENTS.md, CLAUDE.md oder gleichwertig). Das Installationsprogramm gibt diesen Schnipsel zur Erinnerung auch im Terminal aus.

## 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.

Checkliste für Nutzungsvoraussetzungen

Bestätigen Sie für beste Zuverlässigkeit Folgendes:

  1. .vscode/mcp.json enthält den sqlite-project-memory-Server.

  2. Die MCP-Genehmigungs-/Vertrauensaufforderung von VS Code wurde für diesen Arbeitsbereich akzeptiert.

  3. Der Chat befindet sich im Agenten-Modus (nicht im normalen Chat-/Bearbeitungsmodus).

  4. Der Project Memory-Agent ist im Agenten-Dropdown verfügbar.

  5. Die /sqlite-project-memory-Fähigkeit ist in den Slash-Befehlen verfügbar.

  6. Ihre Projektanweisungsdatei enthält den SQLite Project Memory-Schnipsel.

  7. Starten Sie jede Sitzung mit get_project_context und dann get_recent_activity oder query_view.

Das Installationsprogramm gibt einen Usage Gates Report mit PASS oder ACTION REQUIRED für die Gates aus, die es automatisch validieren kann. Wenn Tools immer noch nicht erscheinen, laden Sie VS Code vollständig neu oder starten Sie es neu und beginnen Sie eine neue Agenten-Chat-Sitzung. Wenn der Server nach dem Neustart noch nicht läuft, führen Sie MCP: Start Server aus der Befehlspalette aus, wählen Sie sqlite-project-memory und starten Sie die Chat-Sitzung neu.

Available Tools

41 tools
add_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

    C2.8/5.0

    Scored across 41 tools

    Disambiguation3/5

    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.

    Naming Consistency4/5

    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.

    Tool Count2/5

    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.

    Completeness5/5

    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

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A 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.
      11
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A 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 npm
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      A 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 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A 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