List all Ollama models installed on the local machine with their memory load status.
AI agents call ollama_list_models to retrieve information from Ollama-Omega without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and displays information about installed models and their status. It performs no data modification, deletion, execution, or financial operations. This is a straightforward enumeration/query action typical of the Read category. Severity is low because exposing a list of local models poses minimal direct risk—it reveals system state but does not enable further harmful actions on its own.
From the tool's definition Tool description states 'List all Ollama models installed on the local machine with their memory load status.' This is a pure read operation querying model metadata with no side effects.
Attacks that exploit this kind of access
List all Ollama models installed on the local machine with their memory load status. It is categorised as a Read tool in the Ollama-Omega MCP Server, which means it retrieves data without modifying state.
Register the Ollama-Omega MCP server in PolicyLayer and add a rule for ollama_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 Ollama-Omega. Nothing to install.
ollama_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 ollama_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 ollama_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.
ollama_list_models is provided by the Ollama-Omega MCP server (vrtxomega/ollama-omega). 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 →