analyze_model
AI agents call analyze_model to retrieve information from Instant Meshes without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Analysis tools examine model characteristics (geometry, quality metrics, topology) without creating, modifying, deleting, or executing arbitrary code. The tool fits the Read category as it queries/retrieves model data with no side effects. Low severity because analyzing 3D models poses minimal risk even if misused.
From the tool's definition Tool name 'analyze_model' and server context indicate data retrieval/analysis of 3D model properties without modification. Server description mentions 'quality analysis' as a read-only function.
Attacks that exploit this kind of access
analyze_model. It is categorised as a Read tool in the Instant Meshes MCP Server, which means it retrieves data without modifying state.
Register the Instant Meshes MCP server in PolicyLayer and add a rule for analyze_model: 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 Instant Meshes. Nothing to install.
analyze_model 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 analyze_model 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 analyze_model. 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.
analyze_model is provided by the Instant Meshes MCP server (lxy2109/instant-meshes-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 →