Scrape a URL and return its full HTML content. Restrictions: Activated for URLs that require JavaScript rendering or bot protection. Valid: Get HTML from a dynamic, JS-heavy single-page application. Invalid: Fetching a simple static page (use a standard HTTP client).
AI agents call scrape_html to retrieve information from Scrapeless without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The primary function is data retrieval (Read category). Severity is medium rather than low because: (1) scraping can be used to extract sensitive information from web pages, (2) the tool activates for URLs with bot protection, suggesting it may circumvent access controls, and (3) combined with sibling browser automation tools, it could facilitate unauthorized data collection.
From the tool's definition Tool description states it 'Scrape a URL and return its full HTML content.' This is a retrieval operation with no modification or deletion of data. The tool fetches and returns content without side effects.
Attacks that exploit this kind of access
Scrape a URL and return its full HTML content. Restrictions: Activated for URLs that require JavaScript rendering or bot protection. Valid: Get HTML from a dynamic, JS-heavy single-page application. Invalid: Fetching a simple static page (use a standard HTTP client). It is categorised as a Read tool in the Scrapeless MCP Server, which means it retrieves data without modifying state.
Register the Scrapeless MCP server in PolicyLayer and add a rule for scrape_html: 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 Scrapeless. Nothing to install.
scrape_html 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 scrape_html 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 scrape_html. 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.
scrape_html is provided by the Scrapeless MCP server (scrapeless-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 →