direct_search_csm_models
AI agents call direct_search_csm_models to retrieve information from BlenderMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search and query operations are Read category. The empty description lowers confidence slightly, but the naming convention ('search') and position among sibling tools (which include create, delete, execute, animate operations) strongly suggests this retrieves model data. No side effects or modifications are implied by the name.
From the tool's definition Tool name 'direct_search_csm_models' and sibling context indicate a search/query operation. Description is empty, but naming pattern and server context (CSM.ai 3D assets integration) suggest data retrieval of available models without modification.
Attacks that exploit this kind of access
direct_search_csm_models. It is categorised as a Read tool in the BlenderMCP MCP Server, which means it retrieves data without modifying state.
Register the Blender MCP server in PolicyLayer and add a rule for direct_search_csm_models: 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 BlenderMCP. Nothing to install.
direct_search_csm_models 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 direct_search_csm_models 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 direct_search_csm_models. 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.
direct_search_csm_models is provided by the Blender MCP server (richard-devbot/blender-mcp-csm). 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 →