List models
AI agents call openai_list_models to retrieve information from Anythingllm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool simply enumerates models (likely OpenAI models available to the system), which is a read-only operation with no side effects. The blast radius is minimal—obtaining a list of available models poses no security risk compared to actually using or modifying them.
From the tool's definition Tool name 'openai_list_models' and description 'List models' indicate a retrieval operation that queries available models without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List models. It is categorised as a Read tool in the Anythingllm MCP Server, which means it retrieves data without modifying state.
Register the Anythingllm MCP server in PolicyLayer and add a rule for openai_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 Anythingllm. Nothing to install.
openai_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 openai_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 openai_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.
openai_list_models is provided by the Anythingllm MCP server (moliver28/anythingllm-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 →