AI agents call extract_links to retrieve information from Crawler without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and parses hyperlinks from already-fetched web content. It performs no writes, deletions, code execution, or financial operations. The worst-case misuse (extracting links from sensitive pages) is a data disclosure concern mitigated by the fact that hyperlinks are typically public metadata. Severity is low because the tool itself has minimal blast radius independent of its inputs.
From the tool's definition Tool name 'extract_links' and description 'Extract all hyperlinks from a web page, resolved to absolute URLs' indicate data retrieval with no modification or execution of external operations.
Attacks that exploit this kind of access
Extract all hyperlinks from a web page, resolved to absolute URLs. It is categorised as a Read tool in the Crawler MCP Server, which means it retrieves data without modifying state.
Register the Crawler 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 Crawler. 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 Crawler MCP server (shadab15github/crawler-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 →