list_models
AI agents call list_models to retrieve information from ComfyUI-APP-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or enumerate available models in ComfyUI without modifying state. Listing operations are inherently Read-category. The blast radius of misuse is minimal—an AI agent cannot cause harm by listing models. No destructive, financial, or execute-level risks are evident.
From the tool's definition Tool name 'list_models' indicates a listing/query operation with no side effects. Combined with sibling tools like 'get_template', 'list_templates', and 'read_template_doc', this follows a clear Read pattern.
Attacks that exploit this kind of access
list_models. It is categorised as a Read tool in the ComfyUI-APP-MCP MCP Server, which means it retrieves data without modifying state.
Register the ComfyUI-APP- MCP server in PolicyLayer and add a rule for list_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 ComfyUI-APP-MCP. Nothing to install.
list_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_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_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_models is provided by the ComfyUI-APP- MCP server (luo-lotus/comfyui-app-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →