Skip to content

Commit 16d764e

Browse files
Add PyPI badges and update installation to use uvx
1 parent 0d25958 commit 16d764e

File tree

1 file changed

+19
-21
lines changed

1 file changed

+19
-21
lines changed

README.md

Lines changed: 19 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,9 @@
11
# Neo4j GraphRAG MCP Server
22

3+
[![PyPI version](https://badge.fury.io/py/mcp-neo4j-graphrag.svg)](https://pypi.org/project/mcp-neo4j-graphrag/)
4+
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
5+
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
6+
37
An MCP server that extends Neo4j with **vector search**, **fulltext search**, and **search-augmented Cypher queries** for GraphRAG applications.
48

59
> **Inspired by** the [Neo4j Labs `mcp-neo4j-cypher`](https://github.com/neo4j-contrib/mcp-neo4j/tree/main/servers/mcp-neo4j-cypher) server. This server adds vector search, fulltext search, and the innovative `search_cypher_query` tool for combining search with graph traversal.
@@ -18,34 +22,28 @@ Built on [LiteLLM](https://docs.litellm.ai/) for multi-provider embedding suppor
1822
1923
## Installation
2024

21-
### Step 1: Download the Repository
22-
2325
```bash
24-
git clone https://github.com/guerinjeanmarc/mcp-neo4j-graphrag.git
25-
cd mcp-neo4j-graphrag
26+
# Using pip
27+
pip install mcp-neo4j-graphrag
28+
29+
# Using uv (recommended)
30+
uv pip install mcp-neo4j-graphrag
2631
```
2732

28-
### Step 2: Configure Your MCP Client
33+
## Configuration
2934

30-
#### Claude Desktop
35+
### Claude Desktop
3136

3237
Edit the configuration file:
3338
- **macOS/Linux:** `~/Library/Application Support/Claude/claude_desktop_config.json`
3439
- **Windows:** `%APPDATA%\Claude\claude_desktop_config.json`
3540

36-
Add this server configuration (update the path to where you cloned the repo):
37-
3841
```json
3942
{
4043
"mcpServers": {
4144
"neo4j-graphrag": {
42-
"command": "uv",
43-
"args": [
44-
"--directory",
45-
"/path/to/mcp-neo4j-graphrag",
46-
"run",
47-
"mcp-neo4j-graphrag"
48-
],
45+
"command": "uvx",
46+
"args": ["mcp-neo4j-graphrag"],
4947
"env": {
5048
"NEO4J_URI": "neo4j+s://demo.neo4jlabs.com",
5149
"NEO4J_USERNAME": "recommendations",
@@ -59,11 +57,13 @@ Add this server configuration (update the path to where you cloned the repo):
5957
}
6058
```
6159

62-
#### Cursor
60+
> **Note**: `uvx` automatically downloads and runs the package from PyPI. No local installation needed!
61+
62+
### Cursor
6363

64-
Edit `.cursor/mcp.json` in your project or global settings. Use the same configuration as above.
64+
Edit `~/.cursor/mcp.json` or `.cursor/mcp.json` in your project. Use the same configuration as above.
6565

66-
### Step 3: Reload Configuration
66+
### Reload Configuration
6767

6868
- **Claude Desktop:** Quit and restart the application
6969
- **Cursor:** Reload the window (Cmd/Ctrl + Shift + P → "Reload Window")
@@ -115,9 +115,7 @@ Combine vector/fulltext search with Cypher queries. Use `$vector_embedding` and
115115
**Example prompt:**
116116
> "In one query, what are the directors and genres of the movies about 'time travel adventure' "
117117
118-
## Configuration
119-
120-
### Environment Variables
118+
## Environment Variables
121119

122120
| Variable | Required | Default | Description |
123121
|----------|----------|---------|-------------|

0 commit comments

Comments
 (0)