Discover local LLM models from Ollama and LM Studio.
AI agents call list_local_models to retrieve information from Blender without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about locally installed LLM models from Ollama and LM Studio. It has no side effects, does not execute code, create/modify/delete data, or perform any irreversible actions. It is purely informational (Read category). Severity is low because discovering available models poses minimal security risk even if misused by an AI agent.
From the tool's definition Tool name 'list_local_models' and description 'Discover local LLM models' indicate a query/retrieval operation that lists available models without modification or execution.
Documented attack patterns abuse exactly the kind of access list_local_models gives an agent:
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 list_local_models:
{
"version": "1",
"default": "deny",
"tools": {
"list_local_models": {}
}
}list_local_models is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Discover local LLM models from Ollama and LM Studio. It is categorised as a Read tool in the Blender MCP Server, which means it retrieves data without modifying state.
Register the Blender MCP server in PolicyLayer and add a rule for list_local_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.
list_local_models is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_local_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.
Set action: deny in the PolicyLayer policy for list_local_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.
list_local_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.
Start from Blender, 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.
77 Blender tools catalogued and risk-classified — across an index of 43,000+ MCP servers.