AI agents use resource_unlock 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.
Unlocking a resource is a write operation that modifies state. The severity is medium because unlocking without proper authorization could allow concurrent access to shared resources, creating race conditions or data inconsistency, but the effect is potentially reversible. Not categorized as Execute because it doesn't run arbitrary code—it performs a specific, bounded state change.
From the tool's definition 'Release a resource lock' indicates modification of lock state. While not creating new data, unlocking changes the state of an existing resource (lock record), which is reversible by re-locking.
Attacks that exploit this kind of access
Release a resource lock. 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 resource_unlock: 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.
resource_unlock 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 resource_unlock 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 resource_unlock. 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.
resource_unlock 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 →