cfd_status
AI agents call cfd_status to retrieve information from FreeCAD MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The naming pattern strongly suggests this tool queries or reports the status of CFD simulations rather than modifying or executing them. Status checks are read-only operations with no side effects. Low severity due to information-only nature and bounded scope within CAD simulation context.
From the tool's definition Tool name 'cfd_status' with prefix 'cfd_' (computational fluid dynamics) and 'status' suffix indicates a query/monitoring operation. Sibling tools show 'cfd_build_case' is the action tool; 'cfd_status' retrieves state.
Attacks that exploit this kind of access
cfd_status. It is categorised as a Read tool in the FreeCAD MCP MCP Server, which means it retrieves data without modifying state.
Register the FreeCAD MCP server in PolicyLayer and add a rule for cfd_status: 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.
cfd_status 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 cfd_status 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 cfd_status. 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.
cfd_status 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 →