memento_handoff · Memento MCP: Risk & Policy

WHAT IT DOES

What memento_handoff does on Memento

AI agents use memento_handoff to create or update resources in Memento — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memento environment.

WHY IT NEEDS A POLICY

Why memento_handoff needs a policy

This tool performs a write operation—it generates and persists a checkpoint—but produces no side effects beyond reversible state creation. It does not delete, destroy, or execute external operations. The low severity reflects limited blast radius: a malicious handoff prompt generation or checkpoint corruption would affect only the subsequent session context, not underlying data or external systems.

From the tool's definition Tool creates a checkpoint via 'Create a checkpoint' language, which involves writing/persisting state to the Memento system. The checkpoint mechanism stores a snapshot of the conversation/memory state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memento_handoff Rate-limited

memento_handoff 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "memento_handoff": {
      "limits": [
        {
          "counter": "memento_handoff_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Memento, so you can run agents against it safely.

FAQ

Questions about memento_handoff

What does the memento_handoff tool do? +

[DEPRECATED] Create a checkpoint and generate an LLM-agnostic handoff prompt for continuing in a new chat. It is categorised as a Write tool in the Memento MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on memento_handoff? +

Register the Memento MCP server in PolicyLayer and add a rule for memento_handoff: 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 Memento. Nothing to install.

What risk level is memento_handoff? +

memento_handoff is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit memento_handoff? +

Yes. Add a rate_limit block to the memento_handoff 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.

How do I block memento_handoff completely? +

Set action: deny in the PolicyLayer policy for memento_handoff. 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.

What MCP server provides memento_handoff? +

memento_handoff is provided by the Memento MCP server (joyciakira/memento). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.