Medium Risk

save-preferences

Save user preferences

How to control save-preferences ↓

What save-preferences does on AL Object ID Ninja MCP Server

AI agents use save-preferences to create or update resources in AL Object ID Ninja MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AL Object ID Ninja MCP Server environment.

Medium Risk

Why save-preferences needs a policy

This tool modifies user settings/preferences state within the AL Object ID management system. While preferences are typically reversible (users can update or reset them), the action persists configuration changes that affect system behavior. It qualifies as Write rather than Read (it modifies, not retrieves) and is not Destructive (preferences can be changed again).

From the tool's definition Tool name 'save-preferences' and description 'Save user preferences' indicate creation or modification of user configuration data. The verb 'save' coupled with 'preferences' suggests reversible data modification rather than retrieval or deletion.

Documented attack patterns abuse exactly the kind of access save-preferences gives an agent:

How to control save-preferences

PolicyLayer is an MCP gateway — it sits between your AI agents and AL Object ID Ninja MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for save-preferences:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "save-preferences": {
      "limits": [
        {
          "counter": "save-preferences_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

save-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.

  1. Create a free account and register AL Object ID Ninja MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about save-preferences

What does the save-preferences tool do? +

Save user preferences. It is categorised as a Write tool in the AL Object ID Ninja MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save-preferences? +

Register the AL Object ID Ninja MCP Server MCP server in PolicyLayer and add a rule for save-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 AL Object ID Ninja MCP Server. Nothing to install.

What risk level is save-preferences? +

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

Can I rate-limit save-preferences? +

Yes. Add a rate_limit block to the save-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.

How do I block save-preferences completely? +

Set action: deny in the PolicyLayer policy for save-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.

What MCP server provides save-preferences? +

save-preferences is provided by the AL Object ID Ninja MCP Server MCP server (sshadows/al-objid-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AL Object ID Ninja MCP Server tool call.

Start from AL Object ID Ninja MCP Server, 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.

26 AL Object ID Ninja MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.