Extract all links from a page. Returns a markdown list of links with text
AI agents call web_fetch_links to retrieve information from Smart Webfetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval by extracting and listing hyperlinks from a webpage. It does not modify data, execute code, delete content, or move money. The operation is read-only and produces no side effects beyond returning structured data to the caller. Severity is low because extracted link metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name is 'web_fetch_links' and description states 'Extract all links from a page. Returns a markdown list of links with text' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Extract all links from a page. Returns a markdown list of links with text. It is categorised as a Read tool in the Smart Webfetch MCP Server, which means it retrieves data without modifying state.
Register the Smart Webfetch MCP server in PolicyLayer and add a rule for web_fetch_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 Smart Webfetch. Nothing to install.
web_fetch_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 web_fetch_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 web_fetch_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.
web_fetch_links is provided by the Smart Webfetch MCP server (mathisto/smart-webfetch-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 →