访问指定 URL，提取并清洗页面正文内容，返回干净的 Markdown 格式文本。输入：url（网页地址）。返回：包含标题和 Markdown 内容的对象。
AI agents call read_webpage to retrieve information from Web Search Agent 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 webpage content with no side effects—it only reads and extracts data from remote URLs. This is a pure Read operation. Severity is medium rather than low because webpage access could expose sensitive information if the URL points to private/restricted content, and an agent could be manipulated to scrape confidential pages, though the impact depends entirely on what content exists at…
From the tool's definition Tool name 'read_webpage' and description states it 'accesses specified URL, extracts and cleans page body content, returns clean Markdown format text' with inputs of URL and returns object with title and Markdown content.
Attacks that exploit this kind of access
访问指定 URL，提取并清洗页面正文内容，返回干净的 Markdown 格式文本。输入：url（网页地址）。返回：包含标题和 Markdown 内容的对象。. It is categorised as a Read tool in the Web Search Agent MCP Server, which means it retrieves data without modifying state.
Register the Web Search Agent MCP server in PolicyLayer and add a rule for read_webpage: 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 Search Agent. Nothing to install.
read_webpage 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 read_webpage 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 read_webpage. 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.
read_webpage is provided by the Web Search Agent MCP server (waynepluto/local-web-search-agent). 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 →