Remove a model from local storage
AI agents call remove_model to permanently remove resources in Ollama MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on locally stored models. While the blast radius is limited to the local Ollama instance (not system-wide), removing a model permanently erases data that may be necessary for AI operations. This meets the Destructive category criteria as it is an action that cannot be undone, distinguishing it from Write operations which are reversible.
From the tool's definition Tool name 'remove_model' and description 'Remove a model from local storage' indicate irreversible deletion of data. The action cannot be undone and permanently removes stored model files.
Attacks that exploit this kind of access
Remove a model from local storage. It is categorised as a Destructive tool in the Ollama MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ollama MCP Server MCP server in PolicyLayer and add a rule for remove_model: 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 MCP Server. Nothing to install.
remove_model is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_model 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 remove_model. 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.
remove_model is provided by the Ollama MCP Server MCP server (paolodalprato/ollama-mcp-server). 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 →