Insert a part from the parts library addon.
AI agents use insert_part_from_library 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.
This tool creates or modifies a FreeCAD document by inserting a pre-existing part into it. While it adds content to a design (reversible via undo or delete_object), it does not execute arbitrary code, destroy data irreversibly, or move money. It is a Write operation.
From the tool's definition Tool name is 'insert_part_from_library' and description states it 'Insert[s] a part from the parts library addon.' The verb 'insert' indicates creation/modification of the current FreeCAD document by adding a new component.
Attacks that exploit this kind of access
Insert a part from the parts library addon. 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 insert_part_from_library: 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.
insert_part_from_library 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 insert_part_from_library 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 insert_part_from_library. 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.
insert_part_from_library is provided by the FreeCAD MCP server (lzy-hhhh/freecad). 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 →