Critical Risk →

remove_max_object

Delete a Max object. Args: varname (str): Variable name for the object.

How to control remove_max_object ↓

AI agents call remove_max_object to permanently remove resources in MaxMSP-MCP-Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Deletion of patch objects is a destructive operation that cannot be undone programmatically. An AI agent misusing this tool could permanently remove critical elements from a Max patch (audio processing chains, UI controls, logic flows), disrupting the patch's functionality.

From the tool's definition Tool name is 'remove_max_object' and description explicitly states 'Delete a Max object.' The action is irreversible—once deleted, the object and its configuration within the patch are lost unless manually recreated.

Documented attack patterns abuse exactly the kind of access remove_max_object gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and MaxMSP-MCP-Server, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_max_object:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "remove_max_object"
  ]
}

remove_max_object disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register MaxMSP-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.
RESTRICT THIS TOOL →

Free to start. No card required.

Go deeper

What does the remove_max_object tool do? +

Delete a Max object. Args: varname (str): Variable name for the object. It is categorised as a Destructive tool in the MaxMSP-MCP-Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on remove_max_object? +

Register the MaxMSP-MCP-Server MCP server in PolicyLayer and add a rule for remove_max_object: 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 MaxMSP-MCP-Server. Nothing to install.

What risk level is remove_max_object? +

remove_max_object is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit remove_max_object? +

Yes. Add a rate_limit block to the remove_max_object 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 remove_max_object completely? +

Set action: deny in the PolicyLayer policy for remove_max_object. 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 remove_max_object? +

remove_max_object is provided by the MaxMSP-MCP-Server MCP server (tiianhk/maxmsp-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 MaxMSP-MCP-Server tool call.

Deterministic rules across all 15 MaxMSP-MCP-Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

15 MaxMSP-MCP-Server tools catalogued and risk-classified — across an index of 42,500+ 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.