AI agents call search_polyhaven_assets to retrieve information from Blender without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations are Read category—they query and retrieve data without modifying, deleting, or executing code. Even though the description is empty, the tool name strongly implies a query/search function rather than an action with side effects. The low severity reflects minimal blast radius if misused; searching for 3D assets poses no destructive or system-altering risk.
From the tool's definition Tool name 'search_polyhaven_assets' indicates a search/query operation on PolyHaven assets. The description is empty, but the naming convention and context within a 3D modeling server (alongside download and generation tools) suggest this is a retrieval…
Attacks that exploit this kind of access
search_polyhaven_assets. It is categorised as a Read tool in the Blender MCP Server, which means it retrieves data without modifying state.
Register the Blender MCP server in PolicyLayer and add a rule for search_polyhaven_assets: 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.
search_polyhaven_assets 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 search_polyhaven_assets 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 search_polyhaven_assets. 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.
search_polyhaven_assets is provided by the Blender MCP server (silwings1986/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 →