AI agents invoke crawl_weixin_article to trigger actions in MCP微信公众号爬虫. 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 executes a browser automation process (Selenium) to scrape content from external websites. It triggers external network operations whose effects depend on the target URL arguments, involves automated browser actions, and could be misused to harvest large amounts of content, violate ToS, or conduct unauthorized scraping.
From the tool's definition 爬取微信公众号文章内容和图片 — uses Selenium to automatically crawl/scrape WeChat public account articles and images
Documented attack patterns abuse exactly the kind of access crawl_weixin_article gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP微信公众号爬虫, and nothing reaches the server without passing your rules. This is the rule we recommend for crawl_weixin_article:
{
"version": "1",
"default": "deny",
"tools": {
"crawl_weixin_article": {
"limits": [
{
"counter": "crawl_weixin_article_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}crawl_weixin_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.
爬取微信公众号文章内容和图片. It is categorised as a Execute tool in the MCP微信公众号爬虫 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP微信公众号爬虫 MCP server in PolicyLayer and add a rule for crawl_weixin_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 MCP微信公众号爬虫. Nothing to install.
crawl_weixin_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 crawl_weixin_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 crawl_weixin_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.
crawl_weixin_article is provided by the MCP微信公众号爬虫 MCP server (ditingdapeng/mcpwechatofficialaccounts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP微信公众号爬虫, 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.
3 MCP微信公众号爬虫 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.