Get material properties from BDF model.
AI agents call get_materials 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 retrieves material property data from a Nastran BDF (Bulk Data File) model without creating, modifying, deleting, or executing any operations. It is a passive data access function typical of Read category tools. The blast radius of misuse is minimal—an agent cannot cause harm by repeatedly querying material properties.
From the tool's definition Tool name 'get_materials' and description 'Get material properties from BDF model' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get material properties from BDF 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_materials: 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_materials 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_materials 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_materials. 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_materials 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 →