AI agents call list_edges to retrieve information from Inventor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries geometric data from a 3D model (edge lengths and positions) without any side effects, modifications, or destructive actions. It is a straightforward read operation that returns structured data about the model's geometry.
From the tool's definition Tool name 'list_edges' and description indicating it returns a 'compact edge table' with edge properties (length, midpoint coordinates). No modification, deletion, or execution of operations—purely informational retrieval.
Attacks that exploit this kind of access
Compact edge table of body 1: '[i] L=200.0 mid=(0.0,-225.0,0.8)' per line. It is categorised as a Read tool in the Inventor MCP Server, which means it retrieves data without modifying state.
Register the Inventor MCP server in PolicyLayer and add a rule for list_edges: 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 Inventor. Nothing to install.
list_edges 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 list_edges 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 list_edges. 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.
list_edges is provided by the Inventor MCP server (neonglay/inventor-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 →