AI agents invoke shell_object to trigger actions in FreeCAD Robust MCP Server. 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.
The name 'shell_object' could refer to either a FreeCAD 3D modeling operation (creating a shell/hollow from a solid) or executing shell commands. In the context of a FreeCAD server with 150+ tools, it most likely refers to the 3D Shell feature (hollowing out a solid), which would be a Write/Execute operation modifying geometry. However, the empty description lowers confidence.
From the tool's definition Tool name 'shell_object' in a FreeCAD MCP server context; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access shell_object gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FreeCAD Robust MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for shell_object:
{
"version": "1",
"default": "deny",
"tools": {
"shell_object": {
"limits": [
{
"counter": "shell_object_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}shell_object stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
shell_object. It is categorised as a Execute tool in the FreeCAD Robust MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FreeCAD Robust MCP Server MCP server in PolicyLayer and add a rule for shell_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 Robust MCP Server. Nothing to install.
shell_object 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 shell_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 shell_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.
shell_object is provided by the FreeCAD Robust MCP Server MCP server (spkane/freecad-addon-robust-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 152 FreeCAD Robust MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
152 FreeCAD Robust MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.