// SCAN REPORT

Sketchup Mcp2

22 tools. 14 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

14 can modify or destroy data

8 read-only

22 tools total

Community server · catalogue entry verified 29/06/2026

How to control Sketchup Mcp2 ↓

TOOL MAP

What Sketchup Mcp2 exposes to your agents

Read (8) Write / Execute (13) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Sketchup Mcp2 tools

Destructive · High delete_component Deleting a SketchUp component is an irreversible operation that destroys modeling work. Execute · High transform_component Transforming components in SketchUp modifies the active 3D model's spatial state. Execute · High boolean_operation Boolean operations in SketchUp/3D modeling modify scene geometry, which is closer to Execute or Write. Execute · Medium chamfer_edge Based on the tool name, chamfering an edge in SketchUp modifies 3D geometry by cutting a beveled edge.

14 of Sketchup Mcp2's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sketchup Mcp2

PolicyLayer is an MCP gateway — it sits between your AI agents and Sketchup Mcp2, 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

{
  "find_components": {
    "limits": [
      {
        "counter": "find_components_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 Sketchup Mcp2 — 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 SKETCHUP MCP2 →

Instant setup, no code required.

FULL CATALOGUE

All 22 Sketchup Mcp2 tools

DESTRUCTIVE 1 tools

Destructive delete_component Delete a component by entity ID.

EXECUTE 5 tools

Execute boolean_operation boolean_operation Execute chamfer_edge chamfer_edge Execute eval_ruby eval_ruby Execute fillet_edge fillet_edge Execute transform_component transform_component

WRITE 8 tools

Write create_component create_component Write create_dovetail create_dovetail Write create_finger_joint create_finger_joint Write create_layer Create a new layer with the given name. Returns {id, name, visible}. Write create_mortise_tenon create_mortise_tenon Write export_scene Export the current scene. Note: Ruby tool name is 'export'. Write set_material set_material Write undo Undo the last atomic operation in SketchUp. One MCP tool-call = one undo step.

READ 8 tools

Read find_components Find components matching name substring, layer, and/or type. Read get_component_info Detailed info for a single Group or ComponentInstance by entity ID. Read get_model_info Get current SketchUp model info: file path, title, units, bounding box, entity count, layer list. Read get_selection Get currently selected components. Read get_version get_version Read get_viewport_screenshot get_viewport_screenshot Read list_components List groups and component instances in the model. Read list_layers List all model layers as {name, visible, color, id}.

EXPLORE

Related servers

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

FAQ

Questions about Sketchup Mcp2

Can an AI agent delete data through the Sketchup Mcp2 MCP server? +

Yes. The Sketchup Mcp2 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 Sketchup Mcp2? +

The Sketchup Mcp2 server has 8 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 Sketchup Mcp2.

How many tools does the Sketchup Mcp2 MCP server expose? +

22 tools across 4 categories: Destructive, Execute, Read, Write. 8 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on Sketchup Mcp2? +

Register the Sketchup Mcp2 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 Sketchup Mcp2 tool call.

Deterministic rules across all 22 Sketchup Mcp2 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SKETCHUP MCP2 →

Instant setup, no code required.

22 Sketchup Mcp2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.