list_local_models
Discover local LLM models from Ollama and LM Studio.
This record as markdown: /tools/sandraschi-blender-mcp/list-local-models.md
What list_local_models does on Blender
AI agents call list_local_models to retrieve information from Blender without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_local_models is rated Low
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.
Attacks that exploit this kind of access
The rule that runs list_local_models safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Blender, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_local_models, this is the rule to start with:
list_local_models is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Blender, apply this rule, and every list_local_models call is checked against it from then on.
Questions about list_local_models
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.
More on Blender, and thousands of servers like it.
This server
Across the catalogue