edit_object
AI agents use edit_object to create or update resources in FreeCAD MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FreeCAD MCP environment.
The tool modifies existing CAD objects reversibly. While the empty description reduces confidence, the context from the server description and sibling tools (create_object, delete_object) clearly indicate this performs data modification. It is Write rather than Execute because it targets object properties rather than arbitrary code execution.
From the tool's definition Tool name 'edit_object' combined with server description stating it enables 'editing...objects' in FreeCAD CAD modeling context. Description field is empty, limiting specificity.
Attacks that exploit this kind of access
edit_object. It is categorised as a Write tool in the FreeCAD MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FreeCAD MCP server in PolicyLayer and add a rule for edit_object: 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.
edit_object is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the edit_object 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 edit_object. 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.
edit_object is provided by the FreeCAD MCP server (yaeshio/freecad-mcp-for-ydga). 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 →