AI agents call fetch_url_local 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 page content using a local parser as a fallback mechanism. It performs a read-only operation with no side effects, data modification, code execution, or destructive actions. The blast radius of misuse is minimal—an agent can only retrieve publicly or locally accessible content, not alter it or trigger external operations.
From the tool's definition Tool name 'fetch_url_local' and description '强制使用本地解析器获取网页内容' (force using local parser to fetch web content) indicates retrieval without modification. Server context describes reading and parsing web content with fallback strategies.
Documented attack patterns abuse exactly the kind of access fetch_url_local 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_local:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_url_local": {}
}
}fetch_url_local 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.
强制使用本地解析器获取网页内容（适用于简单网页或Jina不可用时）. 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_local: 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_local 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_local 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_local. 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_local 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.