AI agents call fetch_url to retrieve information from Web Reader 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 web content into Markdown with fallback strategies for access restriction bypass. It performs no side effects—no data is created, modified, deleted, or executed. The bypass mechanisms (paywall, Cloudflare circumvention) are implemented client-side on the retrieval path and do not alter the target server or trigger external operations.
From the tool's definition Tool name 'fetch_url' and description '获取指定URL的网页内容，并转换为Markdown格式' (fetch URL content and convert to Markdown format) indicates retrieval only. No modification, deletion, or execution capabilities mentioned.
Documented attack patterns abuse exactly the kind of access fetch_url gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Web Reader, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_url:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_url": {}
}
}fetch_url 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.
获取指定URL的网页内容，并转换为Markdown格式。默认使用Jina Reader，失败时自动切换到本地解析. It is categorised as a Read tool in the Web Reader MCP Server, which means it retrieves data without modifying state.
Register the Web Reader MCP server in PolicyLayer and add a rule for fetch_url: 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 Reader. Nothing to install.
fetch_url 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_url 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_url. 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_url is provided by the Web Reader MCP server (zacfire/mcp-web-reader). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Web Reader tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Web Reader tools catalogued and risk-classified — across an index of 42,500+ MCP servers.