Project Synapse
🧠 Servidor MCP Project Synapse
Motor de síntesis de conocimiento autónomo con integración LLM-WIKI
Project Synapse es un servidor MCP (Model Context Protocol) que combina una base de datos de grafos Neo4j 2026.x con una wiki de Obsidian Markdown para crear una base de conocimiento persistente y acumulativa. El texto sin procesar se transforma a través de un pipeline semántico en nodos de grafo interconectados con incrustaciones vectoriales (embeddings), mientras que una capa de wiki legible por humanos proporciona páginas Markdown interconectadas y navegables.
📚 Documentación
Para obtener información detallada sobre cómo configurar y utilizar Project Synapse, consulte las siguientes guías:
Primeros pasos: Instalación y primera ejecución.
Arquitectura: Cómo funcionan el pipeline semántico y el grafo.
Configuración: Lista completa de variables de entorno.
Desarrollo: Guía para añadir herramientas y contribuir.
Pruebas: Ejecución de la suite de pruebas.
Contribución: Directrices de contribución al proyecto.
Related MCP server: KG Memory
Qué es (y qué no es) esto
Esto es un sistema de conocimiento, no un editor de código. Está pensado para el pensamiento, la investigación y la escritura que rodean a los proyectos: decisiones de arquitectura, investigación de dominio, justificación de diseño, material de referencia, notas de reuniones.
El código vive en su repositorio. El conocimiento sobre el código vive aquí.
Casos de uso:
Investigaciones profundas que se acumulan durante semanas/meses
Bases de conocimiento de proyectos (por qué se tomaron las decisiones, no solo cuáles fueron)
Gestión de conocimiento personal (artículos, libros, notas de podcasts)
Lluvia de ideas colaborativa con la IA como mantenedora de la wiki
Configuración por proyecto: Cree un vault de Obsidian + repositorio de GitHub independiente para cada proyecto. Apunte la variable de entorno WIKI_VAULT_PATH hacia él. Una instancia de Neo4j puede servir a múltiples proyectos (los grafos coexisten).
Arquitectura
Web / Raw Sources
│
[defuddle] ← cleans web content before ingestion
│
▼
┌──────────────────────┐ ┌─────────────────────┐
│ Semantic Pipeline │────▶│ Neo4j Knowledge │
│ (Montague Grammar, │ │ Graph (entities, │
│ NLP, embeddings) │ │ facts, vectors) │
└──────────────────────┘ └────────┬────────────┘
│
┌───────┴───────┐
│ Wiki Adapter │
└───────┬───────┘
│
┌───────▼───────┐
│ Obsidian Vault│
│ (Markdown, │
│ Git-synced) │
└───────────────┘Características clave
Grafo de conocimiento (Neo4j 2026.x)
Tipo VECTOR nativo con búsqueda semántica ANN
Índices BM25 de texto completo para búsqueda por palabras clave
Búsqueda híbrida (fusión de puntuación vectorial + BM25)
Recorrido de grafos para descubrir relaciones ocultas
Analizador de gramática de Montague para análisis semántico formal
Motor Zettelkasten para la generación autónoma de ideas
Integración LLM-WIKI
Conecta el vault de Obsidian Markdown con el grafo de Neo4j
CRUD completo de páginas con frontmatter YAML
Generación automática de índices y registro de solo adición (append-only)
Comprobaciones de salud: detección de huérfanos, enlaces wiki rotos, frontmatter faltante
Manifiesto de sincronización delta (hashing de contenido) para una sincronización eficiente del grafo
Basado en el patrón LLM Wiki de Andrej Karpathy
Ingesta de contenido web (defuddle)
wiki_fetch_urlobtiene cualquier URL, elimina la navegación/anuncios/desorden mediante defuddle, lo ingesta en Neo4j y lo archiva enClippings/: una sola llamada, totalmente automatizadawiki_ingest_rawmueve automáticamente los archivos procesados deraw/aClippings/: la bandeja de entrada se mantiene limpiaraw/es una verdadera bandeja de entrada: vacía después de cada sesión
Incrustaciones (embeddings) solo locales (sin APIs de pago)
sentence-transformers (predeterminado): se ejecuta en GPU
Ollama (opcional): cualquier modelo de incrustación local
Todos los vectores se almacenan de forma nativa en Neo4j mediante
db.create.setNodeVectorProperty()
Inicio rápido
Requisitos previos
Python 3.12+
Neo4j 2026.x (Community o Enterprise)
Gestor de paquetes uv (
pip install uv)Obsidian con el plugin comunitario Git
Un repositorio de GitHub para el vault de la wiki (puede ser privado)
Node.js + defuddle (para la obtención de contenido web, ver más abajo)
Configuración de Neo4j
# Ubuntu/Debian — see neo4j.com for other platforms
sudo apt install neo4j
sudo systemctl start neo4j
sudo systemctl enable neo4j
# Set password (default user: neo4j)
sudo neo4j-admin set-initial-password your_passwordConfiguración de defuddle
defuddle extrae markdown limpio de páginas web, eliminando la navegación, anuncios y texto repetitivo antes de la ingesta. Requerido para wiki_fetch_url.
# Install Node.js if not present (via nvm recommended)
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash
nvm install --lts
nvm use --lts
# Install defuddle globally
npm install -g defuddle
# Verify
defuddle --versionNota: Synapse encuentra defuddle automáticamente a través de las rutas de nvm incluso si no está en el PATH de su shell. Si
wiki_fetch_urlinforma que no se encuentra defuddle, asegúrese de que esté instalado en una versión de Node gestionada por nvm.
Configuración del vault de Obsidian
Cree un nuevo vault en Obsidian (o clone su repositorio de wiki)
Instale el plugin comunitario Git (Configuración → Plugins comunitarios → Explorar → "Git")
Configure el plugin Git con sus credenciales de GitHub
La estructura del vault (
raw/,wiki/,Clippings/,AGENTS.md) es creada automáticamente por Synapse en la primera ejecución
Instalación
cd /home/ty/Repositories/ai_workspace
git clone <repository-url> project-synapse-mcp
cd project-synapse-mcp
uv venv --python 3.12 --seed
source .venv/bin/activate
uv add -e .
uv run python -m spacy download en_core_web_sm
cp .env.example .env # edit with your Neo4j password and vault pathConfiguración
Edite .env:
NEO4J_URI=bolt://localhost:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=your_password
NEO4J_DATABASE=neo4j
# Embedding — local only, no paid APIs
EMBEDDING_PROVIDER=sentence-transformers # or "ollama"
EMBEDDING_MODEL=sentence-transformers/all-mpnet-base-v2
EMBEDDING_DIMENSION=768
# Wiki vault
WIKI_VAULT_PATH=/path/to/your/obsidian-vault
WIKI_GITHUB_REPO=https://github.com/user/wiki-repoIntegración con Claude Desktop / MCP
Añada a su configuración de MCP:
{
"mcpServers": {
"project-synapse": {
"command": "uv",
"args": [
"--directory", "/path/to/project-synapse-mcp",
"run", "python", "-m", "synapse_mcp.server"
],
"env": {
"NEO4J_URI": "bolt://localhost:7687",
"NEO4J_USER": "neo4j",
"NEO4J_PASSWORD": "your_password",
"NEO4J_DATABASE": "neo4j",
"WIKI_VAULT_PATH": "/path/to/obsidian-vault",
"WIKI_GITHUB_REPO": "https://github.com/user/wiki-repo"
}
}
}
}Herramientas MCP
Grafo de conocimiento
Herramienta | Descripción |
| Procesar texto a través del pipeline semántico → Neo4j |
| Búsqueda semántica vectorial con resultados priorizando ideas |
| Recorrido de grafos para relaciones ocultas |
| Detección autónoma de patrones Zettelkasten |
| Análisis semántico de la gramática de Montague |
Wiki (LLM-WIKI)
Herramienta | Descripción |
| Obtener URL → limpiar con defuddle → ingestar → archivar en Clippings/ |
| Ingestar archivo desde raw/ → Neo4j + mover automáticamente a Clippings/ |
| Crear/actualizar página wiki con frontmatter |
| Leer una página wiki por ruta |
| Búsqueda por palabras clave en páginas wiki |
| Listar todas las páginas en un subdirectorio |
| Reconstruir el índice de la wiki |
| Comprobación de salud: huérfanos, enlaces rotos, frontmatter faltante |
Estructura del vault de la wiki
LLM-WIKI/
├── AGENTS.md # Agent schema doc — conventions and workflows
├── raw/ # INBOX ONLY — unprocessed files; empty after each session
├── raw-inbox.base # Obsidian Base view of pending raw/ queue
├── Clippings/ # Permanent archive — all processed sources land here
├── wiki/
│ ├── index.md # Auto-generated page catalogue
│ ├── log.md # Append-only activity log
│ ├── entities/ # People, tools, projects
│ ├── concepts/ # Ideas, theories, patterns
│ └── sources/ # Summaries of ingested sourcesCiclo de vida del contenido
You clip/save → raw/ # your inbox
or
Agent fetches → wiki_fetch_url # web research
│
[defuddle clean]
│
[semantic pipeline] → Neo4j
│
wiki_write_page → wiki/sources/
│
auto-move → Clippings/ # permanent archiveraw/ siempre está vacío después de una sesión. Clippings/ es el registro permanente de todo lo que se ha procesado. Las páginas fuente en wiki/sources/ hacen referencia a la URL original, no a la ruta del archivo.
Flujo de trabajo
Investigación web:
wiki_fetch_url(url)→ obtiene, limpia, ingesta y archiva en una sola llamadaRecorte manual: Coloque en
raw/, llame awiki_ingest_raw(filename)→ auto-archiva después de la ingestaConsulta:
query_knowledge(grafo) owiki_search(archivos) → sintetizar respuestaLint:
wiki_lint→ corregir huérfanos, enlaces rotos, afirmaciones obsoletasReversión: Git maneja el control de versiones a través del plugin Obsidian Git
Fundamentos teóricos
Gramática de Montague: Semántica composicional formal para la extracción de significado
Método Zettelkasten: Notas vinculadas atómicas con estructura emergente
Teoría de grafos: Detección de comunidades, centralidad, análisis de rutas
LLM-WIKI de Karpathy: Compilación de conocimiento persistente frente a RAG sin estado
Memex de Vannevar Bush: Conocimiento asociativo privado con rutas mantenidas
Licencia
MIT — ver LICENSE.
Project Synapse: De RAG reactivo a conocimiento persistente y acumulativo.
Available Tools
23 toolsanalyze_semantic_structureB
Analyze the semantic structure of text using Montague Grammar parsing.
This tool provides insight into the formal semantic analysis capabilities and shows the logical form translations.
Args: text: Text to analyze semantically include_logical_form: Whether to include the formal logical representation
Returns: Semantic analysis with entities, relations, and optional logical forms
Inputs: text (required), include_logical_form. Returns: result
debug_testB
Simple test tool to check if MCP server is working.
Inputs: no named parameters. Returns: result
explore_connectionsB
Explore connections and relationships around a specific entity in the knowledge graph.
This tool implements the graph traversal capabilities for discovering non-obvious connections and patterns.
Args: entity: Entity name to explore from depth: How many relationship hops to explore (1-5) connection_types: Specific relationship types to follow
Returns: Visual representation of connections and discovered patterns
Inputs: entity (required), depth, connection_types. Returns: result
generate_insightsC
Trigger autonomous insight generation using the Zettelkasten engine.
This tool activates the autonomous synthesis engine to identify patterns and generate novel insights from the existing knowledge graph.
Args: topic: Optional topic to focus insight generation on confidence_threshold: Minimum confidence level for insights (0.0-1.0)
Returns: Generated insights with confidence scores and evidence trails
Inputs: topic, confidence_threshold. Returns: result
ingest_textB
Ingest and process text into the knowledge graph using semantic analysis.
This tool performs the core knowledge synthesis pipeline:
Semantic parsing using Montague Grammar
Entity extraction and relationship identification
Storage in the Neo4j knowledge graph
Automatic insight generation triggers
Args: text: Raw text to process and analyze source: Source identifier for provenance tracking metadata: Additional metadata about the text
Returns: Processing summary with entities and relationships extracted
Inputs: text (required), source, metadata. Returns: result
query_knowledgeA
Query the knowledge graph for facts and insights using natural language.
This tool provides the conversational interface to the knowledge base, prioritizing synthesized insights over raw facts.
Args: query: Natural language query include_insights: Whether to include AI-generated insights max_results: Maximum number of results to return
Returns: Query results with facts, insights, and reasoning trails
Inputs: query (required), max_results, include_insights. Returns: result
synapse_causal_windowA
Find candidate causes by temporal correlation.
Surfaces facts whose valid_from falls in the window
[before - within_days, before] and that share at least one
entity with facts about effect_entity.
This is exactly the "track everything you ate to find what caused the headaches" pattern — you record symptom onset, you record meals and medications, then this tool surfaces co-occurring events as candidates. The tool returns correlation; the human (or a downstream reasoning step) decides what caused what.
Args: effect_entity: The thing whose causes you're hunting (e.g. "headache", "rash", "build failure"). before: ISO date/datetime — when the effect was observed. within_days: How far back to search. Default 30.
Returns: Ranked list of candidate cause-effect pairings with day deltas.
Inputs: before (required), effect_entity (required), within_days. Returns: result
synapse_invalidateA
Mark a previously-recorded fact as no longer true.
Sets valid_to rather than deleting — the historical record stays
intact, but the fact is no longer "currently true" for default queries.
Args: subject/predicate/object: The triple to invalidate. ended: ISO date/datetime when the fact stopped being true. Defaults to now if omitted.
Returns: Number of facts affected.
Inputs: object (required), subject (required), predicate (required), ended. Returns: result
synapse_memory_statsA
Quick stats: how many temporal facts are stored, time span covered.
Inputs: no named parameters. Returns: result
synapse_recallA
Look up time-stamped facts about an entity.
Args:
entity: Name to look up. Matches subject, object, or both depending
on direction.
as_of: ISO date/datetime — if given, only facts valid at this point
in time are returned. Omit for "currently true" facts.
direction: "outgoing" (entity is the subject), "incoming" (entity
is the object), or "both" (default).
Returns: Newline-separated list of facts with timestamps. Empty if none found.
Inputs: entity (required), as_of, direction. Returns: result
synapse_rememberA
Record a time-stamped fact in Synapse's episodic memory.
Use this whenever something is worth remembering across sessions: decisions, observations, "Ty said X on date Y", health/diet/symptom log entries, project milestones.
Args: subject: Who or what the fact is about. Free-form name. predicate: The relationship verb. snake_case preferred (e.g. "started_taking", "moved_to", "decided_to_use"). object: The other side of the relation. valid_from: ISO date or datetime when the fact became true. If omitted, "now" is used. Bare dates → midnight UTC. valid_to: ISO date or datetime when the fact stopped being true. Omit for still-current facts. confidence: 0–1. Default 1.0 for explicit user statements; lower when the agent is inferring. source: Where this fact came from. Defaults to "agent:claude" for things Claude is recording. Use "user" or a filename for facts from explicit user statements or document ingestion. note: Free-form context. Stored in metadata for later recall.
Returns: The fact id (stable content hash — safe to call twice).
Inputs: object (required), subject (required), predicate (required), note, +4 more. Returns: result
synapse_timelineA
Chronological view of remembered facts.
Args: entity: Scope to one entity, or None for the global timeline. limit: Max number of rows. Default 50.
Returns: Time-ordered fact list, oldest first.
Inputs: limit, entity. Returns: result
wiki_cluster_pagesA
Cluster wiki pages by semantic similarity using GAAC (TF-IDF).
Identifies:
Natural topic clusters — pages that belong together
Missing links — same-cluster pages with no wikilink between them
Merge candidates — pages so similar they may be redundant (sim > 0.7)
Args: n_clusters: Number of clusters (auto = sqrt of page count if omitted).
Inputs: n_clusters. Returns: result
wiki_fetch_urlA
Fetch a URL with defuddle (clean markdown extraction), save to raw/, ingest into the knowledge graph, and archive to Clippings/.
Use this when researching the web — it strips navigation and clutter, leaving only the article content. Much cleaner than raw web_fetch.
Args: url: The URL to fetch and process. ingest: If True (default), immediately ingest into Neo4j after saving. Set False to save to raw/ only for manual review first.
Inputs: url (required), ingest. Returns: result
wiki_hits_analysisA
Compute HITS hub and authority scores on the wiki wikilink graph.
Authorities = pages cited by many others — load-bearing knowledge nodes. Hubs = pages that link to many good authorities — navigation layers.
Use to identify which pages need deepening (high authority) and which need comprehensive link coverage (high hub).
Inputs: no named parameters. Returns: result
wiki_ingest_rawA
Read a raw source file and ingest it into both the knowledge graph and wiki.
Reads from raw/, runs it through the Synapse semantic pipeline, stores in Neo4j, and creates a summary page in wiki/sources/.
Args: filename: Filename inside the raw/ directory.
Inputs: filename (required). Returns: result
wiki_lintA
Run a health check on the wiki vault.
Detects orphan pages, broken wikilinks, and missing frontmatter.
Inputs: no named parameters. Returns: result
wiki_list_pagesB
List all markdown pages in the wiki vault with pagination.
Args: subdir: Subdirectory to list ('wiki' or 'raw'). limit: Maximum pages to return (default 50, max 200). offset: Offset for pagination. tag: Filter by tag.
Inputs: tag, limit, offset, subdir. Returns: result
wiki_read_pageB
Read a wiki page.
Args: path: Relative path from vault root (e.g. 'wiki/concepts/rag.md'). mode: What to return: - "meta": metadata/frontmatter only (from index, 0 file reads) - "excerpt": metadata + first 500 characters of page body (from index) - "full": complete page content (reads file from disk)
Inputs: path (required), mode. Returns: result
wiki_searchA
Search wiki pages by keyword.
Args: query: Space-separated search terms. limit: Maximum results to return (default 10). subdir: Scope to subdirectory.
Inputs: query (required), limit, subdir. Returns: result
wiki_sync_indexA
Refresh the wiki index database from disk.
Runs automatically on server start and after write operations. Call manually if files were changed outside Synapse (e.g., Obsidian edits, git pull).
Inputs: no named parameters. Returns: result
wiki_update_indexB
Rebuild the wiki index from all wiki pages.
Args: deep: If True, performs a disk-level verification of all indexed files.
Inputs: deep. Returns: result
wiki_write_pageB
Write or update a wiki page with frontmatter.
Args: path: Relative path (e.g. 'wiki/entities/neo4j.md'). body: Markdown body content. summary: One-line summary for the index. tags: Comma-separated tags.
Inputs: body (required), path (required), tags, summary. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 23 tools
The tools are grouped into wiki, knowledge graph, and memory domains, but several have blurry boundaries: wiki_sync_index vs wiki_update_index, synapse_recall vs synapse_timeline, and ingest_text vs wiki_ingest_raw could cause misselection. Descriptions help clarify most overlaps, but not all.
Most tools follow verb_noun snake_case with clear wiki_ and synapse_ prefixes, but the core knowledge graph tools (ingest_text, query_knowledge, explore_connections) lack a shared prefix and debug_test breaks the pattern. The naming is mostly consistent but not fully systematic.
23 tools is in the heavy range and requires a lot of surface area to navigate, though each tool has a plausible role in the wiki/knowledge-graph/memory system. It is borderline: not overwhelming, but more than is clearly necessary.
The set covers wiki read/write/indexing, knowledge graph ingestion and querying, and episodic memory lifecycle management including invalidation and causal analysis. Minor gaps exist (no wiki page deletion, no explicit knowledge graph entity update/delete), but core workflows are well covered.
Maintenance
Related MCP Connectors
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Personal knowledge graph as an AI memory layer over MCP - read, save, and link your memories.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that transforms markdown notes into an AI-powered knowledge graph. It enables LLM clients to explore, analyze, and diagnose knowledge graphs through tools for node explanation, path finding, causal chain analysis, and wiki health reporting.5MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that implements a heavily typed knowledge graph memory system with AI-powered entity and relation extraction, enabling structured knowledge storage and retrieval from unstructured text using predefined or custom ontologies.9-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that compiles any text into a verifiable, graph-based knowledge base using deterministic chunking and parallel extraction of epistemology primitives.MIT
- AlicenseAqualityBmaintenanceAn MCP server that turns any compatible AI agent into a Zettelkasten partner for creating atomic notes, forming semantic links, detecting clusters, and synthesizing insights from your existing knowledge.192MIT