AI agents use create to create or update resources in My Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your My Memory environment.
The tool creates new data (entities, observations, relationships) in a persistent memory store. This is a Write operation as it modifies the system state reversibly without deleting data. Severity is medium because misuse could lead to pollution of the memory system with false or unwanted information, potentially affecting multiple future conversations.
From the tool's definition Tool name is 'create' and description translates to 'Create new entity/observation/relationship'. This creates new memory records that persist in the system.
Attacks that exploit this kind of access
새로운 엔티티/관찰/관계 생성. It is categorised as a Write tool in the My Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the My Memory MCP server in PolicyLayer and add a rule for create: 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 My Memory. Nothing to install.
create 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 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. 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 is provided by the My Memory MCP server (moontmsai/my-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →