script_execute

A execute tool on the Blender MCP server.

SERVERBlender SOURCEsandraschi/blender-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/sandraschi-blender-mcp/script-execute.md

WHAT IT DOES

What script_execute does on Blender

AI agents invoke script_execute to trigger actions in Blender. 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.

RISK

Why script_execute is rated High

Script execution tools can run arbitrary code within Blender, potentially modifying files, accessing the filesystem, executing system commands through Blender's Python API, or causing unintended side effects depending on script arguments.

From the tool's definition Tool named 'script_execute' on a Blender MCP server that 'Enables AI-powered control of Blender' and allows automation of 3D scenes. The name 'script_execute' directly indicates execution of scripts/code within Blender's environment.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs script_execute safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Blender, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For script_execute, this is the rule to start with:

script_execute Rate-limited

script_execute 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "script_execute": {
      "limits": [
        {
          "counter": "script_execute_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Blender, apply this rule, and every script_execute call is checked against it from then on.

FAQ

Questions about script_execute

What does the script_execute tool do? +

script_execute is a execute tool on the Blender MCP server. It is categorised as a Execute tool in the Blender MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on script_execute? +

Register the Blender MCP server in PolicyLayer and add a rule for script_execute: 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 Blender. Nothing to install.

What risk level is script_execute? +

script_execute is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit script_execute? +

Yes. Add a rate_limit block to the script_execute 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.

How do I block script_execute completely? +

Set action: deny in the PolicyLayer policy for script_execute. 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.

What MCP server provides script_execute? +

script_execute is provided by the Blender MCP server (sandraschi/blender-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Blender, and thousands of servers like it.

This server

All 81 Blender tools → High-risk tools on this server →

Across the catalogue

claude_execute on Claude Bridge →execute_test_case on Percepta MCP Server →load_script on Frida Game Hacking MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →