Fetch a page and return its article content with clutter stripped (no nav, ads, footer, scripts). format: markdown (default), text, both (JSON), html (self-contained reader page), or pdf (typeset reading doc). html/pdf return raw bytes.
AI agents call url.clean to retrieve information from 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 processes publicly accessible web pages to extract article content in various formats (markdown, text, HTML, PDF). It performs no modifications to remote systems, no deletions, no code execution on the host, and no financial transactions. The parsing and formatting operations are transformations applied to fetched data, not side effects on external systems.
From the tool's definition Tool name 'url.clean' and description 'Fetch a page and return its article content' — performs retrieval and parsing of web content without modification or side effects.
Attacks that exploit this kind of access
Fetch a page and return its article content with clutter stripped (no nav, ads, footer, scripts). format: markdown (default), text, both (JSON), html (self-contained reader page), or pdf (typeset reading doc). html/pdf return raw bytes. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for url.clean: 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. Nothing to install.
url.clean 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 url.clean 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 url.clean. 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.
url.clean is provided by the MCP server (@2sio/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 →