Get bounding box of the model.
AI agents call get_model_bounds to retrieve information from pyNastran MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing model data to return bounding box information (min/max coordinates). It performs no data modification, deletion, code execution, or financial operations. It is consistent with other Read-category tools on this server like 'get_nodes', 'get_elements', and 'get_properties'. The blast radius of misuse is minimal since it only exposes geometric bounds information.
From the tool's definition Tool name 'get_model_bounds' and description 'Get bounding box of the model' indicate a read-only query operation that retrieves geometric metadata without modification or side effects.
Attacks that exploit this kind of access
Get bounding box of the model. It is categorised as a Read tool in the pyNastran MCP Server MCP Server, which means it retrieves data without modifying state.
Register the pyNastran MCP Server MCP server in PolicyLayer and add a rule for get_model_bounds: 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 pyNastran MCP Server. Nothing to install.
get_model_bounds 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_model_bounds 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_model_bounds. 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_model_bounds is provided by the pyNastran MCP Server MCP server (shaoqigit/pynastran-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 →