Register a data cloud onto a model cloud using ICP.
AI agents invoke icp_registration to trigger actions in Cloudcompare. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
ICP (Iterative Closest Point) registration is an algorithm that aligns/transforms one point cloud onto another. This executes a computational operation that modifies the spatial position of the data cloud. It writes transformed output data but primarily involves executing a CloudCompare algorithm/command.
From the tool's definition Register a data cloud onto a model cloud using ICP
Attacks that exploit this kind of access
Register a data cloud onto a model cloud using ICP. It is categorised as a Execute tool in the Cloudcompare MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cloudcompare MCP server in PolicyLayer and add a rule for icp_registration: 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 Cloudcompare. Nothing to install.
icp_registration is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the icp_registration 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 icp_registration. 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.
icp_registration is provided by the Cloudcompare MCP server (yufeioptimal/cloudcompare-mcp). 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 →