Generate a Slack/Discord-style link preview card for a URL — title, description, hero image,
AI agents call preview_link to retrieve information from ToolCenter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches public metadata from a URL and formats it for display. It has no side effects, creates no reversible data modifications, executes no code, and poses minimal security risk. It is purely informational (Read category).
From the tool's definition Tool generates a preview card (title, description, hero image) from a URL—it retrieves and displays metadata without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Generate a Slack/Discord-style link preview card for a URL — title, description, hero image,. It is categorised as a Read tool in the ToolCenter MCP MCP Server, which means it retrieves data without modifying state.
Register the ToolCenter MCP server in PolicyLayer and add a rule for preview_link: 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 ToolCenter MCP. Nothing to install.
preview_link 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 preview_link 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 preview_link. 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.
preview_link is provided by the ToolCenter MCP server (toolcenter-dev/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 →