获取网页内容的摘要版本
AI agents call fetch_web_content_summary to retrieve information from URL Fetcher MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and summarizes existing web content without side effects. It is purely informational (Read category). Severity is low because the blast radius of misuse is limited to accessing publicly available information and generating summaries, with no capability to modify data, execute code, or access sensitive resources beyond what public URLs expose.
From the tool's definition Tool description states 'fetch_web_content_summary' which retrieves a summarized version of web content. The server description confirms it 'fetch and analyze web content from URLs' with 'summarization' capabilities.
Attacks that exploit this kind of access
获取网页内容的摘要版本. It is categorised as a Read tool in the URL Fetcher MCP Server MCP Server, which means it retrieves data without modifying state.
Register the URL Fetcher MCP Server MCP server in PolicyLayer and add a rule for fetch_web_content_summary: 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 URL Fetcher MCP Server. Nothing to install.
fetch_web_content_summary 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_web_content_summary 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_web_content_summary. 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_web_content_summary is provided by the URL Fetcher MCP Server MCP server (lucoo01/url-fetcher). 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 →