llm_models

THE RISK

Low Risk

Why llm_models needs a policy

With no description available, the tool's purpose can only be guessed from its name. 'llm_models' likely lists or retrieves available language models, which would be a Read operation. However, given the empty description, confidence is low. Defaulting to Other due to insufficient information, though Read is the most probable category.

From the tool's definition Tool name is 'llm_models' and description is empty or uninformative.

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

POLICY

How to control llm_models

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "llm_models": {
      "limits": [
        {
          "counter": "llm_models_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

llm_models gets a rate cap, and everything else on the server is denied unless you say otherwise.

Create a free account and register Blender — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Blender tools

Destructive clear_scene Remove all objects from the current scene. Execute blender_transform blender_transform Execute script_execute Execute Python script in Blender (headless). Execute agentic_blender_workflow agentic_blender_workflow Execute blender_animation blender_animation Execute blender_geonodes blender_geonodes Execute blender_jobs Async job queue for long-running Blender Python scripts (renders, bakes, sims). Execute blender_particles blender_particles

All 77 Blender tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about llm_models

What does the llm_models tool do? +

llm_models. It is categorised as a Other tool in the Blender MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on llm_models? +

Register the Blender MCP server in PolicyLayer and add a rule for llm_models: 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 Blender. Nothing to install.

What risk level is llm_models? +

llm_models is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit llm_models? +

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

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

llm_models is provided by the Blender MCP server (sandraschi/blender-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Blender tool call.

Start from Blender, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →