Return information about the current Blender scene and all objects in it.
AI agents call get_scene_info to retrieve information from Blender MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves scene metadata and object listings without side effects. It is a read-only operation analogous to listing or fetching data. The sibling tools (create_object, delete_object, execute_python, modify_object) perform write, destructive, and execute actions, but get_scene_info itself only queries state.
From the tool's definition Tool name and description indicate it 'Return[s] information about the current Blender scene and all objects in it' — a pure query operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Return information about the current Blender scene and all objects in it. It is categorised as a Read tool in the Blender MCP MCP Server, which means it retrieves data without modifying state.
Register the Blender MCP server in PolicyLayer and add a rule for get_scene_info: 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 MCP. Nothing to install.
get_scene_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_scene_info 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 get_scene_info. 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.
get_scene_info is provided by the Blender MCP server (nowcika/blender_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →