// SCAN REPORT

SketchupMCP

10 tools. 9 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

9 can modify or destroy data

1 read-only

10 tools total

Community server · catalogue entry verified 11/06/2026

How to control SketchupMCP ↓

TOOL MAP

What SketchupMCP exposes to your agents

Read (1) Write / Execute (8) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous SketchupMCP tools

Destructive · High delete_component Deletion of components in a 3D modeling context is irreversible and cannot be undone programmatically through this tool interface. Execute · High transform_component This tool triggers external operations (geometric transformations) whose effects are determined by the arguments provided (position, rotation, scale values). Execute · Critical eval_ruby 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. Write · Medium create_component Creating a component in Sketchup adds new geometry to a model.

9 of SketchupMCP's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control SketchupMCP

PolicyLayer is an MCP gateway — it sits between your AI agents and SketchupMCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_component": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_component": {
    "limits": [
      {
        "counter": "create_component_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_selection": {
    "limits": [
      {
        "counter": "get_selection_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register SketchupMCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SKETCHUPMCP →

Free to start. No card required.

FULL CATALOGUE

All 10 SketchupMCP tools

DESTRUCTIVE 1 tools

Destructive delete_component Delete a component by ID

EXECUTE 2 tools

Execute transform_component Transform a component's position, rotation, or scale Execute eval_ruby Evaluate arbitrary Ruby code in Sketchup

WRITE 6 tools

Write create_component Create a new component in Sketchup Write create_dovetail Create a dovetail joint between two components Write create_finger_joint Create a finger joint (box joint) between two components Write create_mortise_tenon Create a mortise and tenon joint between two components Write export_scene Export the current scene Write set_material Set material for a component

READ 1 tools

Read get_selection Get currently selected components

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about SketchupMCP

Can an AI agent delete data through the Sketchup MCP server? +

Yes. The SketchupMCP server exposes 1 destructive tools including delete_component. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through SketchupMCP? +

The SketchupMCP server has 6 write tools including create_component, create_dovetail, create_finger_joint. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach SketchupMCP.

How many tools does the Sketchup MCP server expose? +

10 tools across 4 categories: Destructive, Execute, Read, Write. 1 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on SketchupMCP? +

Register the Sketchup MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every SketchupMCP tool call.

Deterministic rules across all 10 SketchupMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SKETCHUPMCP →

Free to start. No card required.

10 SketchupMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.