AI agents invoke evaluate_expression to trigger actions in GOLEM-3DMCP-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.
The name 'evaluate_expression' strongly implies evaluating/executing code or expressions. Given the server's explicit capability to execute arbitrary Python scripts in Rhino 8, this tool likely evaluates expressions or code programmatically. The description is empty, reducing confidence, but the server context and tool name suggest Execute category. Misuse could run arbitrary code in the Rhino environment.
From the tool's definition Tool name 'evaluate_expression' combined with server description stating it can 'execute arbitrary Python scripts' and 'give AI agents direct, programmatic control of Rhino 8'
Documented attack patterns abuse exactly the kind of access evaluate_expression gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GOLEM-3DMCP-Rhino-, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate_expression:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate_expression": {
"limits": [
{
"counter": "evaluate_expression_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}evaluate_expression 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.
Free to start. No card required.
evaluate_expression. It is categorised as a Execute tool in the GOLEM-3DMCP-Rhino- MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GOLEM-3DMCP-Rhino- MCP server in PolicyLayer and add a rule for evaluate_expression: 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 GOLEM-3DMCP-Rhino-. Nothing to install.
evaluate_expression 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 evaluate_expression 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 evaluate_expression. 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.
evaluate_expression is provided by the GOLEM-3DMCP-Rhino- MCP server (thekinghippopotamus/golem-3dmcp-rhino-). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GOLEM-3DMCP-Rhino-, 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.
89 GOLEM-3DMCP-Rhino- tools catalogued and risk-classified — across an index of 43,000+ MCP servers.