Get all links on the current page
AI agents call browser_read_links to retrieve information from Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries link data from a webpage without creating, modifying, deleting, or executing any operations. It is a passive information retrieval operation consistent with Read category tools like 'get' or 'fetch'. The low severity reflects minimal blast radius—an AI agent misusing this tool would only retrieve link information, posing no risk of data loss, financial impact, or unintended execution.
From the tool's definition Tool name 'browser_read_links' and description 'Get all links on the current page' indicate data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access browser_read_links gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Search, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_read_links:
{
"version": "1",
"default": "deny",
"tools": {
"browser_read_links": {}
}
}browser_read_links is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all links on the current page. It is categorised as a Read tool in the Search MCP Server, which means it retrieves data without modifying state.
Register the Search MCP server in PolicyLayer and add a rule for browser_read_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 Search. Nothing to install.
browser_read_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 browser_read_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 browser_read_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.
browser_read_links is provided by the Search MCP server (@agent-infra/mcp-server-search). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Search, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
36 Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.