Create a new memory in the knowledge graph (remember to connect it to related memories). Consider that the memory might already exist, so Search → Create → Connect
AI agents use create_memory to create or update resources in Neo4j Agent Memory MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Neo4j Agent Memory MCP Server environment.
This tool creates new records in a Neo4j graph database. While it is reversible (the server includes delete_memory for removal), it modifies the persistent knowledge store that backs the AI agent's memory system. The blast radius is medium: malicious or incorrect memories could mislead an agent's reasoning, but the damage is confined to that agent's graph and can be undone via delete_memory.
From the tool's definition Tool description explicitly states 'Create a new memory in the knowledge graph', indicating the tool creates/writes data to the Neo4j database.
Documented attack patterns abuse exactly the kind of access create_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Neo4j Agent Memory MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_memory:
{
"version": "1",
"default": "deny",
"tools": {
"create_memory": {
"limits": [
{
"counter": "create_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_memory stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new memory in the knowledge graph (remember to connect it to related memories). Consider that the memory might already exist, so Search → Create → Connect. It is categorised as a Write tool in the Neo4j Agent Memory MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Neo4j Agent Memory MCP Server MCP server in PolicyLayer and add a rule for create_memory: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Neo4j Agent Memory MCP Server. Nothing to install.
create_memory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_memory rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_memory. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_memory is provided by the Neo4j Agent Memory MCP Server MCP server (knowall-ai/mcp-neo4j-agent-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Neo4j Agent Memory MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Neo4j Agent Memory MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.