Fetch a web page and extract all hyperlinks (anchor tags).
AI agents call extract_links to retrieve information from Claude MCP Starter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a web page and parses its HTML to extract hyperlinks. It performs read-only operations: fetching remote content and querying it for links. There is no code execution on the target system, no data modification, and no destructive operations.
From the tool's definition Tool name 'extract_links' and description 'Fetch a web page and extract all hyperlinks (anchor tags)' indicate data retrieval and parsing with no modification or execution of fetched content.
Attacks that exploit this kind of access
Fetch a web page and extract all hyperlinks (anchor tags). It is categorised as a Read tool in the Claude MCP Starter MCP Server, which means it retrieves data without modifying state.
Register the Claude MCP Starter 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 Claude MCP Starter. 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 Claude MCP Starter MCP server (justdreameritis/claude-mcp-starter). 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 →