Scrape content from a URL as Markdown.
AI agents call tool_scrape_url to retrieve information from DevLens 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 extracts data from web pages, converting it to Markdown format. It has no side effects on the target system—it reads existing content without creating, modifying, deleting, or executing operations. The activity is limited to data retrieval, which is characteristic of Read category tools.
From the tool's definition Tool name 'tool_scrape_url' and description 'Scrape content from a URL as Markdown' indicate retrieval and transformation of publicly accessible web content with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Scrape content from a URL as Markdown. It is categorised as a Read tool in the DevLens MCP MCP Server, which means it retrieves data without modifying state.
Register the DevLens MCP server in PolicyLayer and add a rule for tool_scrape_url: 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 DevLens MCP. Nothing to install.
tool_scrape_url 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 tool_scrape_url 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 tool_scrape_url. 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.
tool_scrape_url is provided by the DevLens MCP server (y4nn777/devlens-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 →