Extract all URLs from HTML or plain text content. e.g., an HTML email with 5 anchor tags returns a list of 5 objects with url and anchor text. If no HTML anchor tags found, extracts raw https:// URLs. Use to audit links before sending or to build a links-in-this-issue summary.
AI agents call extract_links to retrieve information from Newsletter Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
extract_links performs passive content analysis by parsing HTML/text and returning structured URL data. No side effects, no modifications, no execution, no financial impact. This is a Read category tool with low severity since URL extraction poses minimal risk even if misused by an AI agent.
From the tool's definition Tool extracts and returns URLs from content without modifying, deleting, or executing anything. Description states it returns 'a list of 5 objects with url and anchor text' and is used to 'audit links' and 'build a links-in-this-issue summary'—pure data…
Attacks that exploit this kind of access
Extract all URLs from HTML or plain text content. e.g., an HTML email with 5 anchor tags returns a list of 5 objects with url and anchor text. If no HTML anchor tags found, extracts raw https:// URLs. Use to audit links before sending or to build a links-in-this-issue summary. It is categorised as a Read tool in the Newsletter Tools MCP Server, which means it retrieves data without modifying state.
Register the Newsletter Tools MCP server in PolicyLayer and add a rule for extract_links: 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 Newsletter Tools. Nothing to install.
extract_links 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 extract_links 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 extract_links. 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.
extract_links is provided by the Newsletter Tools MCP server (josephtandle/beehiiv-mcp-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 →