content_extract_links

Extract all links (<a> elements) from the current page.

SERVERMcp Anything SOURCEZaymadkid/mcp-anything

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/mcp-anything/content-extract-links.md

WHAT IT DOES

What content_extract_links does on Mcp Anything

AI agents call content_extract_links to retrieve information from Mcp Anything without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why content_extract_links is rated Low

This tool performs a query operation that retrieves and lists hyperlink elements from a web page. It has no side effects, does not modify data, execute commands, delete content, or move money. The action is purely informational and read-only.

From the tool's definition Tool name 'content_extract_links' and description 'Extract all links (<a> elements) from the current page' indicate data retrieval with no modification.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs content_extract_links safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Anything, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For content_extract_links, this is the rule to start with:

content_extract_links Allowed

content_extract_links is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "content_extract_links": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Anything, apply this rule, and every content_extract_links call is checked against it from then on.

FAQ

Questions about content_extract_links

What does the content_extract_links tool do? +

Extract all links (<a> elements) from the current page. It is categorised as a Read tool in the Mcp Anything MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on content_extract_links? +

Register the Mcp Anything MCP server in PolicyLayer and add a rule for content_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 Mcp Anything. Nothing to install.

What risk level is content_extract_links? +

content_extract_links is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit content_extract_links? +

Yes. Add a rate_limit block to the content_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.

How do I block content_extract_links completely? +

Set action: deny in the PolicyLayer policy for content_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.

What MCP server provides content_extract_links? +

content_extract_links is provided by the Mcp Anything MCP server (Zaymadkid/mcp-anything). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Anything, and thousands of servers like it.

This server

All 261 Mcp Anything tools →

Across the catalogue

browser_extract_text on Percepta MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →