AI agents use crawlWebsite to create or update resources in MCP-RSS-Crawler — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-RSS-Crawler environment.
The crawlWebsite tool performs a reversible write operation by saving website content to a database. While it has a broad scope (crawling an entire website), the data can be modified or deleted later, making it Write rather than Destructive.
From the tool's definition Tool description states 'save all pages to the database', indicating it creates or modifies data in a persistent store.
Documented attack patterns abuse exactly the kind of access crawlWebsite gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-RSS-Crawler, and nothing reaches the server without passing your rules. This is the rule we recommend for crawlWebsite:
{
"version": "1",
"default": "deny",
"tools": {
"crawlWebsite": {
"limits": [
{
"counter": "crawlwebsite_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}crawlWebsite stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Crawl a website and save all pages to the database. It is categorised as a Write tool in the MCP-RSS-Crawler MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-RSS-Crawler MCP server in PolicyLayer and add a rule for crawlWebsite: 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 MCP-RSS-Crawler. Nothing to install.
crawlWebsite is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the crawlWebsite 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 crawlWebsite. 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.
crawlWebsite is provided by the MCP-RSS-Crawler MCP server (mshk/mcp-rss-crawler). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-RSS-Crawler, 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.
18 MCP-RSS-Crawler tools catalogued and risk-classified — across an index of 43,000+ MCP servers.