Remove a model from memory.
AI agents call model_remove to permanently remove resources in COMSOL MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a model from memory destroys the in-memory representation of a simulation model, which is an irreversible action within the current session. Any unsaved work on that model would be permanently lost. This matches the Destructive category, and the blast radius is high because an entire simulation model (potentially representing significant computational work) can be wiped out.
From the tool's definition 'Remove a model from memory' — the word 'remove' indicates irreversible deletion of the model object from the COMSOL session.
Attacks that exploit this kind of access
Remove a model from memory. It is categorised as a Destructive tool in the COMSOL MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the COMSOL MCP Server MCP server in PolicyLayer and add a rule for model_remove: 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 COMSOL MCP Server. Nothing to install.
model_remove 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 model_remove 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 model_remove. 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.
model_remove is provided by the COMSOL MCP Server MCP server (zhangyoupeng1996/codex_mcp_comsol). 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 →