Skip to main content
Glama
knowall-ai

Neo4j Agent Memory MCP Server

by knowall-ai

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NEO4J_URIYesNeo4j database URI (e.g., bolt://localhost:7687)
NEO4J_DATABASENoNeo4j database name (optional) - For Neo4j Enterprise with multiple databasesneo4j
NEO4J_PASSWORDYesNeo4j password
NEO4J_USERNAMEYesNeo4j username

Tools

Functions exposed to the LLM to take actions

NameDescription
search_memories

Search and retrieve memories from the knowledge graph

create_memory

Create a new memory in the knowledge graph. Consider that the memory might already exist, so Search → Create → Connect (its important to try and connect memories)

create_connection

Create a connection between two memories (its good to have connected memories)

update_memory

Update properties of an existing memory such as adding more detail or make a change when you find out something new

update_connection

Update properties of an existing connection between memories

delete_memory

Delete a memory and all its connections (use with caution - this permanently removes the memory and all its connections)

delete_connection

Delete a specific connection between two memories (use with caution - this permanently removes the relationship)

list_memory_labels

List all unique memory labels currently in use with their counts (useful for getting an overview of the knowledge graph)

get_guidance

Get help on using the memory tools effectively

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/knowall-ai/mcp-neo4j-agent-memory'

If you have feedback or need assistance with the MCP directory API, please join our Discord server