Shorten a URL with optional custom alias. Returns a short URL.
AI agents use shorten_url to create or update resources in LinkShrink MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LinkShrink MCP environment.
The tool creates a new resource (a short URL entry) in the system. This is a Write operation as it modifies state by adding a new URL mapping. It is not Destructive, Financial, or Execute. Severity is low because misuse at worst creates unwanted short URL entries with minimal blast radius.
From the tool's definition 'Shorten a URL with optional custom alias. Returns a short URL.' — creates a new shortened URL mapping, which is a reversible write operation.
Attacks that exploit this kind of access
Shorten a URL with optional custom alias. Returns a short URL. It is categorised as a Write tool in the LinkShrink MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LinkShrink MCP server in PolicyLayer and add a rule for shorten_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 LinkShrink MCP. Nothing to install.
shorten_url is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the shorten_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 shorten_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.
shorten_url 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 →