Get click statistics for a shortened URL
AI agents call url_stats to retrieve information from LinkShrink MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves analytics data (click statistics) for a URL without modifying, deleting, or executing anything. It is a straightforward query operation. Severity is low because even if an AI agent misuses it by querying unauthorized URLs' statistics, the blast radius is limited to information disclosure rather than data modification, deletion, or financial harm.
From the tool's definition Tool name 'url_stats' and description 'Get click statistics for a shortened URL' indicate data retrieval only. The verb 'Get' and the passive nature of statistics collection confirm read-only access with no modifications or side effects.
Attacks that exploit this kind of access
Get click statistics for a shortened URL. It is categorised as a Read tool in the LinkShrink MCP MCP Server, which means it retrieves data without modifying state.
Register the LinkShrink MCP server in PolicyLayer and add a rule for url_stats: 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 LinkShrink MCP. Nothing to install.
url_stats 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 url_stats 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 url_stats. 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.
url_stats is provided by the LinkShrink MCP server (linkshrink-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 →