Convert any URL to clean, LLM-ready Markdown. 84% success rate including JavaScript-heavy sites, Cloudflare-protected pages, and government sites. Renders JavaScript, handles dynamic content, bypasses common bot detection with stealth mode and CAPTCHA solving. Returns structured markdown with tit...
Risk signalsAccepts URL/endpoint input (url)
Part of the Anybrowse server.
Free to start. No card required.
AI agents call scrape to retrieve information from Anybrowse without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though scrape only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"scrape": {}
}
}See the full Anybrowse policy for all 5 tools.
These attack patterns abuse exactly the kind of access scrape gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Convert any URL to clean, LLM-ready Markdown. 84% success rate including JavaScript-heavy sites, Cloudflare-protected pages, and government sites. Renders JavaScript, handles dynamic content, bypasses common bot detection with stealth mode and CAPTCHA solving. Returns structured markdown with title and metadata. Tip: provide 'context' to get more relevant results. Free tier: 10 scrapes per day. Get 50 per day at anybrowse.dev/upgrade-free. It is categorised as a Read tool in the Anybrowse MCP Server, which means it retrieves data without modifying state.
Register the Anybrowse MCP server in PolicyLayer and add a rule for scrape: 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 Anybrowse. Nothing to install.
scrape 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 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. 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 is provided by the Anybrowse MCP server (https://anybrowse.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Anybrowse tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.