提交URL分析：通过11款URL扫描引擎和黑名单服务对URL进行检测，同时分析下载的文件
AI agents invoke url_scan to trigger actions in ThreatMCP. 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.
This tool actively submits a URL to 11 scanning engines, triggers external scanning operations, and downloads files from the target URL. This goes beyond passive reading — it executes scans against external services and fetches remote content, placing it in the Execute category. Misuse could cause unintended scanning of sensitive or malicious URLs, triggering downloads of harmful files.
From the tool's definition 提交URL分析：通过11款URL扫描引擎和黑名单服务对URL进行检测，同时分析下载的文件 — 'submits URL for analysis' and 'downloads files' indicates active execution of scanning engines and file retrieval against external targets
Documented attack patterns abuse exactly the kind of access url_scan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ThreatMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for url_scan:
{
"version": "1",
"default": "deny",
"tools": {
"url_scan": {
"limits": [
{
"counter": "url_scan_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}url_scan 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.
提交URL分析：通过11款URL扫描引擎和黑名单服务对URL进行检测，同时分析下载的文件. It is categorised as a Execute tool in the ThreatMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Threat MCP server in PolicyLayer and add a rule for url_scan: 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 ThreatMCP. Nothing to install.
url_scan 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 url_scan 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 url_scan. 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.
url_scan is provided by the Threat MCP server (naxg/threatmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ThreatMCP, 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.
15 ThreatMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.