Scrape the provided web pages for detailed information.\n\nUse with less than 20 links (most optimally less than 10).\n\nThis tool fetches the content of multiple web pages, processes them to remove images, and returns their combined content. It
AI agents call scrape-webpages to retrieve information from Prospect Research MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns content from external web pages without modifying any data. It is a read/fetch operation. Severity is medium because it can be used to harvest sensitive information from arbitrary URLs at scale (up to 20 pages per call), and could be misused for data exfiltration or scraping private/authenticated pages if credentials are available.
From the tool's definition Scrape the provided web pages for detailed information... fetches the content of multiple web pages, processes them to remove images, and returns their combined content
Attacks that exploit this kind of access
Scrape the provided web pages for detailed information.\n\nUse with less than 20 links (most optimally less than 10).\n\nThis tool fetches the content of multiple web pages, processes them to remove images, and returns their combined content. It. It is categorised as a Read tool in the Prospect Research MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Prospect Research MCP Server MCP server in PolicyLayer and add a rule for scrape-webpages: 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 Prospect Research MCP Server. Nothing to install.
scrape-webpages 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-webpages 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-webpages. 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-webpages is provided by the Prospect Research MCP Server MCP server (jzhang17/prospect-research-mcp). 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 →