Build CDN URL from filename
AI agents call get_cdn_url to retrieve information from Content Automation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool takes a filename as input and constructs a Content Delivery Network URL, which is a read-only operation. It retrieves or generates a URL string for accessing content without side effects, modifying data, or executing external operations. The blast radius is minimal — misuse would only result in incorrect URL construction or access attempts, not data loss or financial impact.
From the tool's definition Tool description: 'Build CDN URL from filename' — performs URL construction/retrieval from a filename without modifying data or triggering external operations.
Attacks that exploit this kind of access
Build CDN URL from filename. It is categorised as a Read tool in the Content Automation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Content Automation MCP Server MCP server in PolicyLayer and add a rule for get_cdn_url: 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 Content Automation MCP Server. Nothing to install.
get_cdn_url 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_cdn_url 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_cdn_url. 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_cdn_url is provided by the Content Automation MCP Server MCP server (ysh-fe/content_automation). 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 →