Fetch and convert webpage content to markdown format. Provide full URL including protocol (http/https). Returns structured text content suitable for analysis.
AI agents call Scrape-Tool to retrieve information from Windows-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and transforms publicly accessible web content into a text format. It performs no side effects, creates no data, executes no code, and modifies no state. The operation is fundamentally a read-only data retrieval mechanism.
From the tool's definition Tool description states 'Fetch and convert webpage content to markdown format' and 'Returns structured text content suitable for analysis.' The verb 'fetch' and the output-only nature (conversion to markdown) indicate data retrieval without modification or…
Attacks that exploit this kind of access
Fetch and convert webpage content to markdown format. Provide full URL including protocol (http/https). Returns structured text content suitable for analysis. It is categorised as a Read tool in the Windows-MCP MCP Server, which means it retrieves data without modifying state.
Register the Windows- MCP server in PolicyLayer and add a rule for Scrape-Tool: 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 Windows-MCP. Nothing to install.
Scrape-Tool 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-Tool 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-Tool. 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-Tool is provided by the Windows- MCP server (zhouke2020/cursortouch-windows-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 →