AI agents use memento_set_goals 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.
This tool creates or modifies AI agent goal data stored in Memento's SQLite temporal graph. While reversible (goals can be changed again), it alters critical autonomous intelligence configuration that governs agent behavior and decision-making. The high severity reflects the substantial blast radius: misconfigured or adversarially injected goals could cause an agent to pursue unintended objectives.
From the tool's definition Tool description states 'Set active goals' and 'Replaces existing goals by default', indicating it modifies persistent state in the temporal graph. The [DEPRECATED] tag and 'stores the reason' confirm data mutation.
Attacks that exploit this kind of access
[DEPRECATED] Set active goals (first-class). Replaces existing goals by default and stores the reason. 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.
Register the Memento MCP server in PolicyLayer and add a rule for memento_set_goals: 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.
memento_set_goals 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 memento_set_goals 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 memento_set_goals. 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.
memento_set_goals 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.
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 →