Project Synapse MCP Server

Autonomous Knowledge Synthesis Engine with LLM-WIKI Integration

Project Synapse is an MCP (Model Context Protocol) server that combines a Neo4j 2026.x graph database with an Obsidian Markdown wiki to create a persistent, compounding knowledge base. Raw text is processed through a semantic pipeline into interconnected graph nodes with vector embeddings, while a human-readable wiki layer provides browsable, interlinked Markdown pages.

For detailed information on setting up and using Project Synapse, please refer to the following guides:

- Getting Started: Installation and first run.
- Architecture: How the semantic pipeline and graph work.
- Configuration: Full list of environment variables.
- Development: Guide for adding tools and contributing.
- Testing: Running the test suite.
- Contributing: Project contribution guidelines.

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) │ └───────────────┘

- NativeVECTORtype with ANN semantic search
- Fulltext BM25 indexes for keyword search
- Hybrid search (vector + BM25 score fusion)
- Graph traversal for discovering hidden relationships
- Montague Grammar parser for formal semantic analysis
- Hybrid Extraction Pipeline: Merges LLM-based extraction (Gemma 2 9b via Ollama) with spaCy NER for high-precision entity and relationship discovery
- Zettelkasten engine for autonomous insight generation

- Bridges Obsidian Markdown vault with the Neo4j graph
- Full page CRUD with YAML frontmatter
- Automatic index generation and append-only log
- Health checks: orphan detection, broken wikilinks, missing frontmatter
- Delta-sync manifest (content hashing) for efficient graph sync
- Based onAndrej Karpathy's LLM Wiki pattern

- Python 3.12+
- Neo4j 2026.x(Community or Enterprise)
- uv package manager (pip install uv)
- Obsidianwith theGit community plugin
- A GitHub repo for the wiki vault (can be private)
- Node.js + defuddle (for web content fetching — see below)

# 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_password

# 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 --version

cd /path/to/your/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 path

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 # Extraction — Montague (default) or "llm" (hybrid) EXTRACTION_PROVIDER=montague OLLAMA_EXTRACTION_MODEL=gemma2:9b OLLAMA_TIMEOUT=120 # Wiki vault WIKI_VAULT_PATH=/path/to/your/obsidian-vault WIKI_GITHUB_REPO=https://github.com/user/wiki-repo

{ "mcpServers": { "project-synapse": { "command": "uv", "args": [ "--directory", "/path/to/project-synapse-mcp", "run", "python", "-m", "synapse_mcp.server" ] } } }

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 sources

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 archive

raw/is always empty after a session.Clippings/is the permanent record of everything that's been processed. Source pages inwiki/sources/reference the original URL, not the file path.
- Web research:wiki_fetch_url(url)→ fetches, cleans, ingests, archives in one call
- Manual clip: Drop intoraw/, callwiki_ingest_raw(filename)→ auto-archives after ingest
- Query:query_knowledge(graph) orwiki_search(files) → synthesize answer
- Lint:wiki_lint→ fix orphans, broken links, stale claims
- Rollback: Git handles version control via Obsidian Git plugin

- Montague Grammar: Formal compositional semantics for meaning extraction
- Zettelkasten Method: Atomic linked notes with emergent structure
- Graph Theory: Community detection, centrality, path analysis
- Karpathy LLM-WIKI: Persistent knowledge compilation vs stateless RAG
- Vannevar Bush's Memex: Private associative knowledge with maintained trails

Project Synapse: From reactive RAG to persistent, compounding knowledge.

Neo4j graph database server (schema + read/write-cypher) and separate graph database backed memory

Query a Neo4j graph database containing a knowledge graph of German family businesses.

Integrate the Neo4j graph database with clients through natural language interactions.

A scalable knowledge graph memory system for LLMs with semantic retrieval and temporal awareness, using Neo4j as a backend.

A knowledge graph memory server using the Neo4j graph database to store and retrieve information from AI interactions.

Manages personal knowledge using a local Neo4j container, with data imported from JSON files.

Manage graph-based data models, schemas, and ontologies with CoreModels. 16 MCP tools for visual data modeling with full JSON Schema support.

Interact with CrateDB using natural language for Text-to-SQL queries and documentation retrieval.

Query and interact with FalkorDB graph databases using AI models.

An MCP server for graph-based memory management, enabling AI to create, retrieve, and manage knowledge entities and their relationships.