MCP server for Graphiti knowledge graph operations with Neo4j integration
Project description
Graphiti-Memory MCP Server
A Model Context Protocol (MCP) server that provides memory and knowledge graph operations using Neo4j and the Graphiti framework.
Features
- 🧠 Memory Node Search: Query nodes in your knowledge graph
- 🔗 Fact Search: Search for relationships and facts
- 🔍 Connection Diagnostics: Test Neo4j authentication and connectivity
- 📊 Real-time Data: Returns actual data from your Neo4j database
- 🛠️ Built-in Diagnostics: Comprehensive error messages and troubleshooting
Installation
Prerequisites
-
Neo4j Database: You need a running Neo4j instance
# Install Neo4j (via Homebrew on macOS) brew install neo4j # Start Neo4j neo4j start
-
Python 3.8+: Required for the MCP server
Install from PyPI
pip install graphiti-memory
Install from Source
git clone https://github.com/alankyshum/graphiti-memory.git
cd graphiti-memory
pip install -e .
Configuration
MCP Configuration
Add to your MCP client configuration file (e.g., ~/.captain/mcp.json or Claude Desktop config):
{
"mcpServers": {
"graphiti-memory": {
"command": "graphiti-mcp-server",
"env": {
"NEO4J_URI": "neo4j://127.0.0.1:7687",
"NEO4J_USER": "neo4j",
"NEO4J_PASSWORD": "your-password-here"
}
}
}
}
Neo4j Setup
-
Set Password (first-time setup):
neo4j-admin dbms set-initial-password YOUR_PASSWORD
-
Test Connection:
# HTTP interface curl http://127.0.0.1:7474 # Bolt protocol nc -zv 127.0.0.1 7687
Available Tools
1. search_memory_nodes
Search for nodes in the Neo4j knowledge graph.
Example:
{
"name": "search_memory_nodes",
"arguments": {
"query": "machine learning"
}
}
Returns: List of nodes with IDs, labels, and properties.
2. search_memory_facts
Search for facts and relationships in the knowledge graph.
Example:
{
"name": "search_memory_facts",
"arguments": {
"query": "related concepts"
}
}
Returns: Fact triples (subject-predicate-object) with metadata.
3. test_neo4j_auth
Test Neo4j authentication and return connection diagnostics.
Example:
{
"name": "test_neo4j_auth",
"arguments": {}
}
Returns: Connection status, URI, user, and diagnostic information.
Usage
With Captain (LinkedIn's MCP Client)
After installation and configuration, the tools are automatically available:
# Test connection
mcp_captain_graphiti-memory_test_neo4j_auth({})
# Search for nodes
mcp_captain_graphiti-memory_search_memory_nodes({"query": "test"})
With Claude Desktop
Configure in ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"graphiti-memory": {
"command": "graphiti-mcp-server",
"env": {
"NEO4J_URI": "neo4j://127.0.0.1:7687",
"NEO4J_USER": "neo4j",
"NEO4J_PASSWORD": "your-password"
}
}
}
}
Standalone Testing
Test the server directly from command line:
export NEO4J_URI="neo4j://127.0.0.1:7687"
export NEO4J_USER="neo4j"
export NEO4J_PASSWORD="your-password"
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}' | graphiti-mcp-server
Troubleshooting
Connection Failed
Error: Connection refused or ServiceUnavailable
Solutions:
- Check Neo4j is running:
neo4j status - Start Neo4j:
neo4j start - Verify port 7687 is accessible:
nc -zv 127.0.0.1 7687
Authentication Failed
Error: Unauthorized or authentication failure
Solutions:
- Verify password is correct
- Reset password:
neo4j-admin dbms set-initial-password NEW_PASSWORD - Update password in MCP configuration
- Use test tool to verify:
test_neo4j_auth
Package Not Found
Error: neo4j package not installed
This package automatically installs the neo4j dependency. If you see this error:
pip install neo4j
Development
Setup Development Environment
git clone https://github.com/alankyshum/graphiti-memory.git
cd graphiti-memory
pip install -e ".[dev]"
Running Tests
# Test the server
python -m graphiti_memory.server << 'EOF'
{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}
EOF
Architecture
MCP Client (Captain/Claude)
↓
Graphiti-Memory Server
↓
Neo4j Database
The server:
- Listens on stdin for JSON-RPC messages
- Logs diagnostics to stderr
- Responds on stdout with JSON-RPC
- Maintains persistent Neo4j connection
Contributing
Contributions welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
License
MIT License - see LICENSE file for details.
Links
- GitHub: https://github.com/alankyshum/graphiti-memory
- PyPI: https://pypi.org/project/graphiti-memory/
- Issues: https://github.com/alankyshum/graphiti-memory/issues
- MCP Specification: https://modelcontextprotocol.io
Credits
Built for use with:
- Model Context Protocol (MCP)
- Neo4j
- Captain - LinkedIn's MCP client
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file graphiti_memory-0.1.2.tar.gz.
File metadata
- Download URL: graphiti_memory-0.1.2.tar.gz
- Upload date:
- Size: 8.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b65af49d883be4024e787016c228e398f2891d2829f092b695a90a69235ccad2
|
|
| MD5 |
6616d90dea08cce3094f1f4fddeab7b2
|
|
| BLAKE2b-256 |
40c2f81a957460397031ca8d3640df4defc0cfd0714a9bed74724210f2163585
|
File details
Details for the file graphiti_memory-0.1.2-py3-none-any.whl.
File metadata
- Download URL: graphiti_memory-0.1.2-py3-none-any.whl
- Upload date:
- Size: 9.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f70ae3f117431d904c31b61b5f0869431ce8b288c74de5c640e600274597edd1
|
|
| MD5 |
a0c25a78bf6b8bf9d24f793f0018dcd0
|
|
| BLAKE2b-256 |
03c2301d63cf8e03517efe788f714de6be0fee716aac2a6ec8942554986c6ec9
|