fem_run
AI agents invoke fem_run to trigger actions in FreeCAD MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of external finite element simulations whose outcomes depend on input parameters (mesh configuration, material properties, boundary conditions, etc.). Such execution can consume significant computational resources and produce results that guide downstream decisions. While not destructive of data and not financial, it represents a computational operation with real-world consequences.
From the tool's definition Tool name 'fem_run' indicates execution of finite element method (FEM) simulations. The server description mentions 'structural analysis' as a capability, and 'fem_run' is positioned among tools that create BIM objects and perform complex CAD operations.
Attacks that exploit this kind of access
fem_run. It is categorised as a Execute tool in the FreeCAD MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FreeCAD MCP server in PolicyLayer and add a rule for fem_run: 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 FreeCAD MCP. Nothing to install.
fem_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the fem_run 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 fem_run. 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.
fem_run is provided by the FreeCAD MCP server (sandraschi/freecad-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 →