AI agents use register_agent 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.
This tool creates or modifies agent records in the memory system, which is a reversible operation consistent with Write category. The severity is low because registration is a benign administrative action with minimal blast radius — it does not execute arbitrary code, delete data, move money, or access sensitive information without explicit intent. The idempotent behavior further reduces risk.
From the tool's definition Tool name and description indicate it registers/creates an agent record. Description states it is 'Idempotent' and 'same name returns existing agent', implying creation or modification of agent metadata. No deletion or irreversible change occurs.
Attacks that exploit this kind of access
Register an agent. Idempotent — same name returns existing agent. 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 register_agent: 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.
register_agent 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 register_agent 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 register_agent. 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.
register_agent 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 →