scrapling_crawl
Start a multi-page spider crawl with extraction. Crawls from start URLs, follows links matching a CSS selector, extracts data per page. Returns a session_id to poll with scrapling_crawl_status. Max 500 pages, 1-20 concurrent. Domain whitelist enforced. Use for SEC filing crawls, news aggregation,...
This record as markdown: /tools/io-github-homenshum-nodebench/scrapling-crawl.md
What scrapling_crawl does on Nodebench
AI agents invoke scrapling_crawl to trigger actions in Nodebench. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why scrapling_crawl is rated High
This tool initiates a multi-page web spider with configurable parameters (start URLs, CSS selectors, concurrency 1-20). It performs external operations (HTTP requests, link following, data extraction) whose behavior and side effects depend entirely on user-supplied arguments. While not reading/writing the local system, it executes network operations against external targets, classifying it as Execute.
From the tool's definition Crawls from start URLs, follows links matching a CSS selector, extracts data per page; triggering external web operations whose effects depend on arguments (target URLs, selectors, concurrency)
Attacks that exploit this kind of access
The rule that runs scrapling_crawl 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 scrapling_crawl, this is the rule to start with:
scrapling_crawl stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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 scrapling_crawl call is checked against it from then on.
Questions about scrapling_crawl
Start a multi-page spider crawl with extraction. Crawls from start URLs, follows links matching a CSS selector, extracts data per page. Returns a session_id to poll with scrapling_crawl_status. Max 500 pages, 1-20 concurrent. Domain whitelist enforced. Use for SEC filing crawls, news aggregation, or site-wide data collection. Requires Scrapling bridge server. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for scrapling_crawl: 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.
scrapling_crawl is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the scrapling_crawl 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 scrapling_crawl. 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.
scrapling_crawl 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.
Across the catalogue