Update a preference in Chen
AI agents use update_preference to create or update resources in Chen's AI Copy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chen's AI Copy environment.
This tool creates or modifies user preference data without permanently destroying it. Updates are reversible (preferences can be changed again), so it does not qualify as Destructive. It does not execute arbitrary code or run external operations (Execute), move money (Financial), or merely retrieve data (Read). It fits the Write category as a reversible data modification tool.
From the tool's definition Tool name is 'update_preference' and description states it will 'Update a preference in Chen', indicating modification of stored user data. The server manages 'user preferences and career interests', which are reversible data changes.
Attacks that exploit this kind of access
Update a preference in Chen. It is categorised as a Write tool in the Chen's AI Copy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chen's AI Copy MCP server in PolicyLayer and add a rule for update_preference: 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 Chen's AI Copy. Nothing to install.
update_preference 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 update_preference 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 update_preference. 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.
update_preference is provided by the Chen's AI Copy MCP server (shenchensucc/chens-ai-copy). 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 →