AI agents use memory_pin to create or update resources in Mementos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mementos environment.
Pinning/unpinning a memory changes its state or retrieval priority but does not create, delete, or destroy data. It is a reversible Write operation. Severity is medium because misuse could suppress important memories from an agent's accessible context, potentially affecting decision-making, but the operation itself is not destructive and can be undone.
From the tool's definition Tool name 'memory_pin' and description 'Pin or unpin a memory' indicates modification of metadata (pin state) associated with stored memories. This is a reversible change—pinning and unpinning can be toggled.
Attacks that exploit this kind of access
Pin or unpin a memory by ID or key. No version needed. It is categorised as a Write tool in the Mementos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mementos MCP server in PolicyLayer and add a rule for memory_pin: 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 Mementos. Nothing to install.
memory_pin 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 memory_pin 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 memory_pin. 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.
memory_pin is provided by the Mementos MCP server (@hasna/mementos). 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 →