AI agents call fetch_links to retrieve information from Web Fetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs passive data extraction of link metadata from web pages. It retrieves existing hyperlinks without modifying content, executing code, or triggering side effects. The operation is informational in nature—similar to parsing a page's navigation structure. No destructive, financial, or execution capabilities are present.
From the tool's definition Tool extracts hyperlink titles and addresses from a page, with description stating it discovers page navigation structure and external resources. The terms 'extract' and 'discover' indicate data retrieval with no modification or execution.
Attacks that exploit this kind of access
提取页面中所有超链接的标题和地址，用于发现页面导航结构和外部资源. It is categorised as a Read tool in the Web Fetch MCP Server, which means it retrieves data without modifying state.
Register the Web Fetch MCP server in PolicyLayer and add a rule for 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 Web Fetch. Nothing to install.
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 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 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.
fetch_links is provided by the Web Fetch MCP server (xiaozhuabcd1234/web-fetch-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 →