AI agents call remove_points_by_class to permanently remove resources in Metashape MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes point cloud data by classification, which is irreversible. Once points are deleted from a 3D model in Metashape, they cannot be recovered without reprocessing. This qualifies as Destructive rather than Write. The high severity reflects the potential loss of significant photogrammetry work products.
From the tool's definition Tool name 'remove_points_by_class' explicitly indicates deletion/removal of point cloud data. No description provided, but the verb 'remove' in a photogrammetry context (alongside sibling tools like 'add_marker', 'align_cameras', 'build_contours') strongly…
Documented attack patterns abuse exactly the kind of access remove_points_by_class gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Metashape MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_points_by_class:
{
"version": "1",
"default": "deny",
"hide": [
"remove_points_by_class"
]
} remove_points_by_class disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
remove_points_by_class. It is categorised as a Destructive tool in the Metashape MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Metashape MCP Server MCP server in PolicyLayer and add a rule for remove_points_by_class: 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 Metashape MCP Server. Nothing to install.
remove_points_by_class 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_points_by_class 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_points_by_class. 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_points_by_class is provided by the Metashape MCP Server MCP server (jenkinsm13/metashape-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Metashape MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
112 Metashape MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.