AI agents invoke eval_ruby to trigger actions in SketchupMCP. 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.
This tool executes arbitrary Ruby code within SketchUp, which means it can perform any operation the Ruby environment allows — including file system access, process execution, data deletion, and network calls. 'Arbitrary' code execution has an unbounded blast radius, making this critical severity.
From the tool's definition "Evaluate arbitrary Ruby code in Sketchup"
Documented attack patterns abuse exactly the kind of access eval_ruby gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SketchupMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for eval_ruby:
{
"version": "1",
"default": "deny",
"tools": {
"eval_ruby": {
"limits": [
{
"counter": "eval_ruby_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}eval_ruby 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 arbitrary Ruby code in Sketchup. It is categorised as a Execute tool in the SketchupMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sketchup MCP server in PolicyLayer and add a rule for eval_ruby: 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 SketchupMCP. Nothing to install.
eval_ruby 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 eval_ruby 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 eval_ruby. 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.
eval_ruby is provided by the Sketchup MCP server (mhyrr/sketchup-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SketchupMCP, 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.
10 SketchupMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.