update_preference · Adaptive Agent MCP: Risk & Policy

WHAT IT DOES

What update_preference does on Adaptive Agent

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

WHY IT NEEDS A POLICY

Why update_preference needs a policy

The tool name and server context strongly suggest this creates or modifies user preference records reversibly. This is a Write operation rather than Read (query-only), Execute (triggering external operations), or Destructive (permanent deletion). Severity is medium because misuse could alter user behavior tracking and personalization settings, but effects are reversible via subsequent updates.

From the tool's definition Tool name 'update_preference' combined with server's stated purpose of 'autonomously read and write memory' and 'continuously learning and adapting user preferences' indicates this tool modifies user preference data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_preference Rate-limited

update_preference 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": {
    "update_preference": {
      "limits": [
        {
          "counter": "update_preference_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 Adaptive Agent, so you can run agents against it safely.

FAQ

Questions about update_preference

What does the update_preference tool do? +

update_preference. It is categorised as a Write tool in the Adaptive Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_preference? +

Register the Adaptive Agent 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 Adaptive Agent. Nothing to install.

What risk level is update_preference? +

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

Can I rate-limit update_preference? +

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.

How do I block update_preference completely? +

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.

What MCP server provides update_preference? +

update_preference is provided by the Adaptive Agent MCP server (justforever17/adaptive-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.