AI agents call crawl_wechat_article to retrieve information from Crawl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and transforms existing content from WeChat articles and images. It performs read-only operations (fetching, downloading, converting format) without creating, modifying, deleting, or executing arbitrary code. The conversion to Markdown is a presentation transformation, not data mutation. No side effects beyond the intended data retrieval and local storage occur.
From the tool's definition Tool description indicates 'crawl' and 'get' operations: '抓取微信公众号文章内容' (fetch WeChat official account article content), '自动图片下载' (automatic image download), and 'Markdown转换' (Markdown conversion).
Documented attack patterns abuse exactly the kind of access crawl_wechat_article gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crawl, and nothing reaches the server without passing your rules. This is the rule we recommend for crawl_wechat_article:
{
"version": "1",
"default": "deny",
"tools": {
"crawl_wechat_article": {}
}
}crawl_wechat_article is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
抓取微信公众号文章内容，支持自动图片下载和Markdown转换. It is categorised as a Read tool in the Crawl MCP Server, which means it retrieves data without modifying state.
Register the Crawl MCP server in PolicyLayer and add a rule for crawl_wechat_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 Crawl. Nothing to install.
crawl_wechat_article is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crawl_wechat_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_wechat_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_wechat_article is provided by the Crawl MCP server (wutongci/crawl-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Crawl tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Crawl tools catalogued and risk-classified — across an index of 42,500+ MCP servers.