This record as markdown: /tools/caravanglory-cocos-mcp-server/remove-reference-image.md
What remove_reference_image does on Cocos
AI agents call remove_reference_image to permanently remove resources in Cocos, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why remove_reference_image is rated Critical
Removing reference images is a destructive action that irreversibly deletes data. While the blast radius is scoped to reference images rather than critical project assets, an AI agent could maliciously or erroneously delete all reference images from a project, hindering the designer's workflow and losing work.
From the tool's definition Tool name 'remove_reference_image' indicates deletion operation. Description states 'Remove reference image(s)' using imperative verb 'remove', which in the context of asset management constitutes irreversible deletion.
Attacks that exploit this kind of access
The rule that runs remove_reference_image safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cocos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For remove_reference_image, this is the rule to start with:
remove_reference_image is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Cocos, apply this rule, and every remove_reference_image call is checked against it from then on.
Questions about remove_reference_image
Remove reference image(s). It is categorised as a Destructive tool in the Cocos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cocos MCP server in PolicyLayer and add a rule for remove_reference_image: 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 Cocos. Nothing to install.
remove_reference_image 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_reference_image 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_reference_image. 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_reference_image is provided by the Cocos MCP server (caravanglory/cocos-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cocos, and thousands of servers like it.
Across the catalogue