Neo4j MCP Chainlit
About
A poc of Neo4j mcp server with Chainlit (MCP host) and Claude LLM (Anthropic) API
Details
- Author
- Abhid14
- Downloads
- 160
- Categories
- AI
Jump to
- Web chat interface powered by Chainlit
- Natural language queries via Claude (Anthropic API)
- Database access through Neo4j’s Model Context Protocol
- Pre-configured sample Neo4j database (Movie Graph)
- Proof-of-concept demonstrating MCP + LLM integration
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Neo4j MCP ChainlitCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, install uv, create a Python virtual environment, install dependencies from requirements.txt, and set your ANTHROPIC_API_KEY in a .env file. Start the app with chainlit run app.py -w. Then configure an MCP connection inside the Chainlit interface: use stdio mode, name it neo4j-mcp-demo, and set the command to /path/to/uv/binary/uvx mcp-neo4j-cypher --db-url neo4j+s://demo.neo4jlabs.com --user recommendations --password recommendations.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"neo4j mcp chainlit": {
"neo4j-mcp-chainlit": {
"command": "uv",
"args": [
"venv"
]
}
}
}
}McpServers
{
"neo4j-mcp-chainlit": {
"command": "uv",
"args": [
"venv"
]
}
}Neo4j MCP Chainlit
A proof of concept demonstrating integration between Neo4j MCP server with Chainlit (MCP host) and Claude LLM (Anthropic API).
Overview
This project creates an interactive chat interface to query Neo4j databases using natural language. It leverages:
- Chainlit for the web interface
- Neo4j's MCP (Model Context Protocol) for database access
- Claude from Anthropic as the LLM for natural language understanding
Quick Start Guide
Prerequisites
1. Clone the repository:
git clone https://github.com/Abhid14/neo4j-mcp-chainlit.git
cd neo4j-mcp-chainlit
2. Install uv on your system:
curl -LsSf https://astral.sh/uv/install.sh | sh
For additional installation options, check the uv documentation.
Setup
1. Create a Python virtual environment:
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
2. Install dependencies:
uv pip install -r requirements.txt
3. Configure environment variables:
cp .env.example .env
4. Add your Anthropic API key to the .env file:
ANTHROPIC_API_KEY=your_api_key_here
Running the Application
Start the Chainlit app:
chainlit run app.py -w
Configure MCP Connections
1. In the Chainlit app interface, configure MCP connections
2. Use the sample Neo4j database:
- Set the MCP connection in stdio mode
- Name it neo4j-mcp-demo
- Set the Command to:
/path/to/uv/binary/uvx mcp-neo4j-cypher --db-url neo4j+s://demo.neo4jlabs.com --user recommendations --password recommendations
Demo
The application uses the Neo4j demo database (Movie Graph) to demonstrate natural language querying capabilities.
Try asking questions like:
- "What movies did Tom Hanks act in?"
- "Show me the relationship between actors and directors"
- "Find all movies released after 2010"
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
