cfd_read_results
AI agents call cfd_read_results 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 tool reads/retrieves CFD (computational fluid dynamics) simulation results without modifying, executing, or deleting anything. It is a read-only operation with minimal side effects, consistent with the Read category. Low severity because accessing simulation output poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'cfd_read_results' indicates retrieval of simulation data; no 'delete', 'modify', 'execute', or 'write' keywords present. Description is empty, limiting confidence slightly.
Attacks that exploit this kind of access
cfd_read_results. 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_read_results: 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_read_results 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_read_results 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_read_results. 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_read_results 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 →