AI agents call raycast 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.
Raycasting is a fundamental spatial query operation in 3D environments. It retrieves information about the world state (what objects exist at certain coordinates) without side effects. The tool takes origin and direction parameters to perform the query and returns hit information.
From the tool's definition Tool description states 'Cast a ray in the 3D world and return hit information.' The raycast operation queries the 3D scene for collision data without modifying, executing external code, deleting, or initiating financial transactions.
Attacks that exploit this kind of access
Cast a ray in the 3D world and return hit information. Args: - origin (number[]): Ray origin [x, y, z] - direction (number[]): Ray direction [x, y, z] - filterType (string, optional):. 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 raycast: 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.
raycast 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 raycast 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 raycast. 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.
raycast 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 →