AI agents call web_extract to retrieve information from Onion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
web_extract retrieves and parses public webpage content to present structured metadata and text. There are no side effects, no data modification, no code execution, and no destructive operations. This is a standard read operation. The low severity reflects minimal risk: the tool simply fetches and formats existing web data, with blast radius limited to information disclosure of already-public content.
From the tool's definition Tool description states it 'extracts structured information from webpage URL: title, description, body summary, all links.' The verbs 'extract' and the information types (title, description, summary, links) indicate read-only data retrieval with no…
Attacks that exploit this kind of access
从网页 URL 提取结构化信息：标题、描述、正文摘要、所有链接。. It is categorised as a Read tool in the Onion MCP Server, which means it retrieves data without modifying state.
Register the Onion MCP server in PolicyLayer and add a rule for web_extract: 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 Onion. Nothing to install.
web_extract 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 web_extract 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 web_extract. 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.
web_extract is provided by the Onion MCP server (onion-ai/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
web_extract is one line of Onion's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →