fetch_url
Fetch a URL and extract its content as markdown, text, or raw HTML. Useful for reading documentation, blog posts, API references, and web pages. Uses linkedom for HTML parsing when available, with fallback to basic text extraction.
This record as markdown: /tools/io-github-homenshum-nodebench/fetch-url.md
What fetch_url does on Nodebench
AI agents call fetch_url to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why fetch_url is rated Low
This is a straightforward content retrieval tool with no side effects. It parses and extracts data from remote URLs but does not execute code, modify state, delete resources, or commit financial transactions. The fallback to basic text extraction and use of linkedom for parsing confirms it is designed for safe content consumption only.
From the tool's definition 'Fetch a URL and extract its content as markdown, text, or raw HTML' — the tool retrieves and reads web content without modifying, deleting, or executing code. It explicitly supports 'reading documentation, blog posts, API references, and web pages.'
Attacks that exploit this kind of access
The rule that runs fetch_url safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fetch_url, this is the rule to start with:
fetch_url is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every fetch_url call is checked against it from then on.
Questions about fetch_url
Fetch a URL and extract its content as markdown, text, or raw HTML. Useful for reading documentation, blog posts, API references, and web pages. Uses linkedom for HTML parsing when available, with fallback to basic text extraction. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for fetch_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 Nodebench. Nothing to install.
fetch_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 fetch_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 fetch_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.
fetch_url is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue