AI agents call get_bounding_box to retrieve information from Melo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure query operation that retrieves spatial information from an instance. It has no side effects, does not execute code, does not modify state, and does not delete data. The blast radius of misuse is minimal—an agent could only retrieve unwanted geometric information, not cause damage to the project or environment.
From the tool's definition Tool 'Get the axis-aligned bounding box of an instance (and its descendants)' retrieves geometric metadata about an instance without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Get the axis-aligned bounding box of an instance (and its descendants). Args: - path (string): Instance path Returns: { center: [x, y, z], size: [x, y, z], min: [x, y, z], max: [x, y, z] }. It is categorised as a Read tool in the Melo MCP Server, which means it retrieves data without modifying state.
Register the Melo MCP server in PolicyLayer and add a rule for get_bounding_box: 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 Melo. Nothing to install.
get_bounding_box 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 get_bounding_box 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 get_bounding_box. 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.
get_bounding_box is provided by the Melo MCP server (yannyhl/linkedsword-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 →