Remove a model
AI agents call rm to permanently remove resources in Ollama — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible delete operation on Ollama models. Even though the blast radius is limited to removing a specific model (rather than system-wide data), the action cannot be undone and represents permanent data loss, making it Destructive rather than Write.
From the tool's definition Tool name 'rm' combined with description 'Remove a model' indicates irreversible deletion of a model from the Ollama server. This is destructive because the deletion cannot be undone and results in permanent loss of the model artifact.
Attacks that exploit this kind of access
Remove a model. It is categorised as a Destructive tool in the Ollama MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ollama MCP server in PolicyLayer and add a rule for rm: 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. Nothing to install.
rm 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 rm 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 rm. 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.
rm is provided by the Ollama MCP server (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 →