Scrape web pages - fetch HTML, extract elements, get links, images, text, metadata
AI agents call web_scrape to retrieve information from MCP Workspace Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches and extracts content from web pages (HTML, links, images, text, metadata), which are read-only operations. However, severity is medium because it can access arbitrary external URLs outside the sandboxed workspace, potentially exfiltrating data or being used to fetch malicious content, and network requests do leave traces on external servers.
From the tool's definition 'Scrape web pages - fetch HTML, extract elements, get links, images, text, metadata' — all retrieval/query operations with no stated side effects
Attacks that exploit this kind of access
Scrape web pages - fetch HTML, extract elements, get links, images, text, metadata. It is categorised as a Read tool in the MCP Workspace Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Workspace Server MCP server in PolicyLayer and add a rule for web_scrape: 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 MCP Workspace Server. Nothing to install.
web_scrape 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_scrape 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_scrape. 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_scrape is provided by the MCP Workspace Server MCP server (shayyeffet/ultimate_mcp_server). 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 →