AI agents call get_material_purchase_urls to retrieve information from Kiln without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly suggests it retrieves or looks up purchase URLs for 3D printer materials, which is a passive data retrieval operation with no side effects. Without a description, confidence is moderate, but the semantic meaning of 'get_' combined with the read-only nature of URL lookup justifies a Read category with low severity.
From the tool's definition Tool name 'get_material_purchase_urls' indicates retrieval of URLs; no description provided to suggest modification or destructive intent. The prefix 'get_' is a strong indicator of a read operation.
Attacks that exploit this kind of access
get_material_purchase_urls. It is categorised as a Read tool in the Kiln MCP Server, which means it retrieves data without modifying state.
Register the Kiln MCP server in PolicyLayer and add a rule for get_material_purchase_urls: 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 Kiln. Nothing to install.
get_material_purchase_urls 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_material_purchase_urls 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_material_purchase_urls. 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_material_purchase_urls is provided by the Kiln MCP server (codeofaxel/Kiln). 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 →