Clone/download an entire website with all its pages and assets.
AI agents invoke clone_website to trigger actions in WebClone MCP Server. 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.
Cloning an entire website involves crawling multiple pages, downloading all assets, and storing them — this triggers extensive external network operations whose scope and impact depend entirely on the target URL argument. It is not a simple read (it writes to local storage and hammers the remote server), not purely destructive, but constitutes a broad external operation.
From the tool's definition Clone/download an entire website with all its pages and assets
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access clone_website gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WebClone MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for clone_website:
{
"version": "1",
"default": "deny",
"tools": {
"clone_website": {
"limits": [
{
"counter": "clone_website_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}clone_website 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.
Free to start. No card required.
Clone/download an entire website with all its pages and assets. It is categorised as a Execute tool in the WebClone MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the WebClone MCP Server MCP server in PolicyLayer and add a rule for clone_website: 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 WebClone MCP Server. Nothing to install.
clone_website 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 clone_website 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 clone_website. 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.
clone_website is provided by the WebClone MCP Server MCP server (ruslanmv/webclone). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WebClone MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 WebClone MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.