Neo4j Vectordb
MCP server that mimics a pure vector database using Neo4j - vector search, fulltext search, NO graph traversal. Designed to compare Vector RAG vs GraphRAG effectiveness. Uses OpenAI embeddings. Built with FastMCP.
Ask AI about Neo4j Vectordb
Powered by Claude Β· Grounded in docs
I know everything about Neo4j Vectordb. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Neo4j VectorDB MCP Server
An MCP server that uses Neo4j as a pure vector database β no graph traversal, no relationships.
Purpose
This server is designed to compare Vector RAG vs Graph RAG. It provides the same search capabilities as mcp-neo4j-graphrag but intentionally hides graph features, allowing you to measure the value that graph context adds to LLM responses.
| Feature | mcp-neo4j-vectordb (This) | mcp-neo4j-graphrag |
|---|---|---|
| Vector search | β | β |
| Fulltext search | β | β |
| Graph traversal | β | β |
| Cypher queries | β | β |
| Relationships | β Hidden | β Visible |
Installation
Step 1: Download the Repository
git clone https://github.com/guerinjeanmarc/mcp-neo4j-vectordb.git
cd mcp-neo4j-vectordb
Step 2: Configure Claude Desktop
Edit the configuration file:
- macOS/Linux:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add this server configuration (update the path to where you cloned the repo):
{
"mcpServers": {
"neo4j-vectordb": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-neo4j-vectordb",
"run",
"mcp-neo4j-vectordb"
],
"env": {
"NEO4J_URI": "neo4j+s://demo.neo4jlabs.com",
"NEO4J_USERNAME": "recommendations",
"NEO4J_PASSWORD": "recommendations",
"NEO4J_DATABASE": "recommendations",
"OPENAI_API_KEY": "sk-...",
"EMBEDDING_MODEL": "text-embedding-ada-002"
}
}
}
}
Step 3: Reload Configuration
Quit and restart Claude Desktop to load the new configuration.
Tools
get_searchable_content
Discover available indexes and searchable node properties (no relationships shown).
π‘ The agent should automatically call this tool first to understand what can be searched.
Example prompt:
"What can I search in this database?"
vector_search
Semantic similarity search.
Example prompt:
"Find movies about 'a hero's journey in space'"
fulltext_search
Keyword search with Lucene syntax.
Example prompt:
"Where was Tom Hanks born??"
get_node_by_id
Retrieve a node's properties by ID (no relationships).
Example prompt:
"Get the full details of the first movie from my search results"
Comparison Workflow: Vector RAG vs Graph RAG
Use both servers to compare how graph context improves LLM responses.
Prerequisites
Download both repositories:
git clone https://github.com/guerinjeanmarc/mcp-neo4j-vectordb.git
git clone https://github.com/guerinjeanmarc/mcp-neo4j-graphrag.git
Step 1: Configure Both Servers in Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"neo4j-vectordb": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-neo4j-vectordb",
"run",
"mcp-neo4j-vectordb"
],
"env": {
"NEO4J_URI": "neo4j+s://demo.neo4jlabs.com",
"NEO4J_USERNAME": "recommendations",
"NEO4J_PASSWORD": "recommendations",
"NEO4J_DATABASE": "recommendations",
"OPENAI_API_KEY": "sk-...",
"EMBEDDING_MODEL": "text-embedding-ada-002"
}
},
"neo4j-graphrag": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-neo4j-graphrag",
"run",
"mcp-neo4j-graphrag"
],
"env": {
"NEO4J_URI": "neo4j+s://demo.neo4jlabs.com",
"NEO4J_USERNAME": "recommendations",
"NEO4J_PASSWORD": "recommendations",
"NEO4J_DATABASE": "recommendations",
"OPENAI_API_KEY": "sk-...",
"EMBEDDING_MODEL": "text-embedding-ada-002"
}
}
}
}
Step 2: Test with VectorDB Only
- In Claude Desktop, click the "Search and Tools" button in the conversation interface
- Disable
neo4j-graphragtools (keep onlyneo4j-vectordbactive) - Ask the test question:
"Find movies about artificial intelligence, and tell me which directors have made multiple AI films and what other genres they typically work in."
- Note Claude's answer and what tools it used
Step 3: Test with GraphRAG Only
- Click "Search and Tools" again
- Disable
neo4j-vectordbtools and enableneo4j-graphragtools - Ask:
"You have now access to the Neo4j tools, please answer the same question."
- Note Claude's answer and what tools it used
Step 4: Compare Results
Ask Claude to compare:
"Compare your two previous answers. What approach gave you better context to answer the question? Please explain what technology is better to answer the question: VectorDB or Neo4j?"
Example Questions for Comparison
| Question | Vector RAG | Graph RAG |
|---|---|---|
| "What is The Matrix about?" | β Good | β Good |
| "Find sci-fi movies" | β Good | β Good |
| "Which actors worked with both Spielberg and Nolan?" | β οΈ Limited | β Excellent |
| "What genres does Tom Hanks typically act in?" | β οΈ Limited | β Excellent |
| "Find movies similar to Inception and show their directors' other work" | β οΈ Limited | β Excellent |
Configuration
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
NEO4J_URI | Yes | bolt://localhost:7687 | Neo4j connection URI |
NEO4J_USERNAME | Yes | neo4j | Neo4j username |
NEO4J_PASSWORD | Yes | password | Neo4j password |
NEO4J_DATABASE | No | neo4j | Database name |
EMBEDDING_MODEL | No | text-embedding-3-small | Embedding model |
Embedding Providers
Supports all LiteLLM embedding providers:
- OpenAI:
text-embedding-ada-002,text-embedding-3-small - Azure:
azure/deployment-name - Bedrock:
bedrock/amazon.titan-embed-text-v1 - Cohere:
cohere/embed-english-v3.0 - Ollama:
ollama/nomic-embed-text
Related
- mcp-neo4j-graphrag β Full GraphRAG with graph traversal
- Neo4j MCP Documentation
- Official Neo4j MCP Server
License
MIT License
