rhino_shell
Hollow a closed Brep, optionally leaving the listed faces open.
This record as markdown: /tools/easehee-rhino-mcp/rhino-shell.md
What rhino_shell does on Rhino
AI agents invoke rhino_shell to trigger actions in Rhino. 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.
Why rhino_shell is rated High
There is a significant mismatch between the tool name 'rhino_shell' (which implies shell/command execution) and the description (which describes a Rhino geometry operation - shelling a Brep). Given the server context (Rhino 8/Grasshopper geometry tool), the description is likely accurate and this is a geometry modification operation (Write/Execute level).
From the tool's definition Tool is named 'rhino_shell' but description says 'Hollow a closed Brep, optionally leaving the listed faces open.' The name 'rhino_shell' strongly suggests executing a shell command, but the description describes a geometry operation in Rhino.
Attacks that exploit this kind of access
The rule that runs rhino_shell safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Rhino, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For rhino_shell, this is the rule to start with:
rhino_shell stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Rhino, apply this rule, and every rhino_shell call is checked against it from then on.
Questions about rhino_shell
Hollow a closed Brep, optionally leaving the listed faces open. It is categorised as a Execute tool in the Rhino MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Rhino MCP server in PolicyLayer and add a rule for rhino_shell: 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 Rhino. Nothing to install.
rhino_shell 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 rhino_shell 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 rhino_shell. 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.
rhino_shell is provided by the Rhino MCP server (easehee/rhino-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Rhino, and thousands of servers like it.
Across the catalogue