Load a .form file from disk and create a new scene from it.
AI agents call load_form to retrieve information from Formlabs Local without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (.form file) from disk and imports it into the application. While it does create a new scene, the primary operation is file I/O reading. There are no irreversible deletions, code execution, financial transactions, or side effects beyond loading data into memory. The scene creation is a reversible operation (it can be deleted via delete_scene).
From the tool's definition Tool name is 'load_form' and description states it 'Load[s] a .form file from disk and create a new scene from it.' The action is reading/loading a file from disk into the application.
Attacks that exploit this kind of access
Load a .form file from disk and create a new scene from it. It is categorised as a Read tool in the Formlabs Local MCP Server, which means it retrieves data without modifying state.
Register the Formlabs Local MCP server in PolicyLayer and add a rule for load_form: 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 Formlabs Local. Nothing to install.
load_form 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 load_form 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 load_form. 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.
load_form is provided by the Formlabs Local MCP server (mkebiclioglu/formlabs-local-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 →