Read or update user preferences: default style, aspect ratio, model, style notes, and favorite prompts. Call with action
AI agents use manage_preferences to create or update resources in MeiGen AI Design MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MeiGen AI Design MCP environment.
While read operations alone would be Read category, the explicit mention of 'update' capability means this tool can modify stored user configuration data. This is reversible (preferences can be changed again), so it falls under Write rather than Destructive. Severity is medium because misuse could alter user experience settings or favorite data, but doesn't cause irreversible loss or execute arbitrary code.
From the tool's definition Tool performs 'Read or update user preferences' — the update capability makes this a Write operation that modifies user-controlled settings like 'default style, aspect ratio, model, style notes, and favorite prompts.'
Documented attack patterns abuse exactly the kind of access manage_preferences gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MeiGen AI Design MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for manage_preferences:
{
"version": "1",
"default": "deny",
"tools": {
"manage_preferences": {
"limits": [
{
"counter": "manage_preferences_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}manage_preferences 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.
Free to start. No card required.
Read or update user preferences: default style, aspect ratio, model, style notes, and favorite prompts. Call with action. It is categorised as a Write tool in the MeiGen AI Design MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MeiGen AI Design MCP server in PolicyLayer and add a rule for manage_preferences: 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 MeiGen AI Design MCP. Nothing to install.
manage_preferences 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 manage_preferences 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 manage_preferences. 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.
manage_preferences is provided by the MeiGen AI Design MCP server (jau123/meigen-ai-design-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MeiGen AI Design MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 MeiGen AI Design MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.