Neo4j Memory

​

Prerequisites

• Docker installed (for running the MCP server image)
• Meshagent CLI installed and authenticated (Get Started)
• Neo4j database running (local or remote instance)
• Meshagent account

​

Required Environment Variables

Set these environment variables with your Neo4j database credentials and connection string:

• NEO4J_URL – e.g. bolt://host.docker.internal:7687
• NEO4J_USERNAME – e.g. neo4j
• NEO4J_PASSWORD – e.g. password

​

Steps

1. Install Meshagent with all plugins:

   Copy

   Ask AI

   pip install "meshagent[all]"
   

2. Sign up and authenticate with Meshagent:

   • Visit: Meshagent CLI Get Started
   • Follow instructions to login.

3. Launch the MCP server as a Meshagent service in a room:

   Copy

   Ask AI

   meshagent service test \
     --room=test \
     --role=agent \
     --image=meshagent/mcp-neo4j-memory:latest \
     --env MESHAGENT_PORT=8001 \
     --env NEO4J_URL=<bolt://your-neo4j-host:7687> \
     --env NEO4J_USERNAME=<your-neo4j-username> \
     --env NEO4J_PASSWORD=<your-neo4j-password> \
     --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" \
     --name=mcp-neo4j-memory-service
   

   • This launches the Neo4j Memory MCP server within the Meshagent room.
   • Note: Replace the angle-bracket values (<...>) with your actual Neo4j instance details.
   • Rooms will close if they go inactive.

4. Start a chatbot in the Meshagent room with the Neo4j-memory toolkit:

   Copy

   Ask AI

   meshagent chatbot join \
     --room=test \
     --agent-name=sample \
     --name=sample \
     --toolkit=mcp-neo4j-memory
   

   • This starts a chatbot with access to all mcp-neo4j-memory tools.
   • You can load multiple toolkits for an agent in the same room.
   • After running, a link to the room will be provided in the output for browser-based interaction.

​

Tools Available

Below is an overview of the tools this MCP server provides for graph-based memory with Neo4j:

​

Tools Details

​

add_observations

Add new observations to existing entities in the knowledge graph

​

create_entities

Create multiple new entities in the knowledge graph

​

create_relations

Create multiple new relations between entities in the knowledge graph. Relations should be in active voice.

​

delete_entities

Delete multiple entities and their associated relations from the knowledge graph

​

delete_observations

Delete specific observations from entities in the knowledge graph

​

delete_relations

Delete multiple relations from the knowledge graph

​

find_nodes

Find specific nodes in the knowledge graph by their names

​

open_nodes

Open specific nodes in the knowledge graph by their names

​

read_graph

Read the entire knowledge graph

​

search_nodes

Search for nodes in the knowledge graph based on a query

​

Meshagent & Neo4j Memory MCP Resources

• Meshagent: https://www.meshagent.com/
• Getting Started with Room API: https://docs.meshagent.com/room_api/get_started
• Room API Overview: https://docs.meshagent.com/room_api/overview
• Meshagent MCP Neo4j Memory Docker Image: https://hub.docker.com/r/meshagent/mcp-neo4j-memory