memento_check_goal_alignment · Memento MCP: Risk & Policy

WHAT IT DOES

What memento_check_goal_alignment does on Memento

AI agents invoke memento_check_goal_alignment to trigger actions in Memento. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why memento_check_goal_alignment needs a policy

The tool runs submitted code or plans through an enforcement/evaluation pipeline, which constitutes executing an external operation whose effects depend on arguments. While it may be read-like in intent (checking alignment), enforcement implies side effects such as blocking, modifying, or flagging actions. The DEPRECATED status and vague description lower confidence.

From the tool's definition 'Submit code or plans to be strictly evaluated' and 'Level 2 Enforcer' — implies active evaluation/enforcement logic is triggered against project goals

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memento_check_goal_alignment Rate-limited

memento_check_goal_alignment stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_check_goal_alignment": {
      "limits": [
        {
          "counter": "memento_check_goal_alignment_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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_check_goal_alignment

What does the memento_check_goal_alignment tool do? +

[DEPRECATED] Level 2 Enforcer: Submit code or plans to be strictly evaluated against the project. It is categorised as a Execute tool in the Memento MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on memento_check_goal_alignment? +

Register the Memento MCP server in PolicyLayer and add a rule for memento_check_goal_alignment: 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_check_goal_alignment? +

memento_check_goal_alignment is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit memento_check_goal_alignment? +

Yes. Add a rate_limit block to the memento_check_goal_alignment 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_check_goal_alignment completely? +

Set action: deny in the PolicyLayer policy for memento_check_goal_alignment. 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_check_goal_alignment? +

memento_check_goal_alignment 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.