Extract a (possibly paywalled) article by trying a fallback ladder: live page → archive.today → Wayback → 12ft.io. Each candidate is loaded IN the stealth browser and parsed with Readability, then quality-gated. Returns the first clean result, tagged with the method that won.
AI agents invoke crow_browser_extract_article to trigger actions in Crow. 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.
The tool actively launches a stealth browser, navigates to external URLs (including paywall-bypass services), and executes page parsing logic. This constitutes external operation execution rather than a simple read/fetch. The paywall-bypass mechanism (12ft.io, archive.today) adds risk as it could be misused to circumvent access controls.
From the tool's definition 'loaded IN the stealth browser' and 'trying a fallback ladder: live page → archive.today → Wayback → 12ft.io' — triggers external browser operations and HTTP requests to multiple external services
Documented attack patterns abuse exactly the kind of access crow_browser_extract_article gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_browser_extract_article:
{
"version": "1",
"default": "deny",
"tools": {
"crow_browser_extract_article": {
"limits": [
{
"counter": "crow_browser_extract_article_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} crow_browser_extract_article 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.
Extract a (possibly paywalled) article by trying a fallback ladder: live page → archive.today → Wayback → 12ft.io. Each candidate is loaded IN the stealth browser and parsed with Readability, then quality-gated. Returns the first clean result, tagged with the method that won. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crow MCP server in PolicyLayer and add a rule for crow_browser_extract_article: 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 Crow. Nothing to install.
crow_browser_extract_article 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 crow_browser_extract_article 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 crow_browser_extract_article. 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.
crow_browser_extract_article is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.