执行网页搜索，返回搜索结果列表。 支持多源专业搜索，根据搜索目标选择合适的 category： 类别说明： - general: 通用网页搜索（默认） - science: 学术论文、研究（arxiv, google scholar, pubmed等） - it: IT技术（github, stackoverflow, npm, pypi, docker hub等） - social media: 社交媒体讨论（lemmy, mastodon等） - news: 新闻资讯 - images: 图片搜索 - videos: 视频搜索 - files: 文件搜索 使用建议： - 搜索论文时使...
AI agents call web_search to retrieve information from Wuxing Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure read/retrieval tool. It queries web search engines and returns results to the user with no side effects, no data modification, no code execution, and no destructive operations. The search parameters allow filtering by category and other criteria, but these are query options, not actions that modify state.
From the tool's definition Tool description states '执行网页搜索，返回搜索结果列表' (executes web search, returns search results list). The tool performs searches across multiple sources and returns results without modifying, deleting, or executing any data.
Documented attack patterns abuse exactly the kind of access web_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Wuxing Search MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for web_search:
{
"version": "1",
"default": "deny",
"tools": {
"web_search": {}
}
}web_search 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.
执行网页搜索，返回搜索结果列表。 支持多源专业搜索，根据搜索目标选择合适的 category： 类别说明： - general: 通用网页搜索（默认） - science: 学术论文、研究（arxiv, google scholar, pubmed等） - it: IT技术（github, stackoverflow, npm, pypi, docker hub等） - social media: 社交媒体讨论（lemmy, mastodon等） - news: 新闻资讯 - images: 图片搜索 - videos: 视频搜索 - files: 文件搜索 使用建议： - 搜索论文时使用 category: science - 搜索代码/技术问题时使用 category: it - 查看社区讨论时使用 category: social media - 全面搜索（论文+代码+讨论+资讯）使用 category: [. It is categorised as a Read tool in the Wuxing Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Wuxing Search MCP server in PolicyLayer and add a rule for web_search: 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 Wuxing Search MCP. Nothing to install.
web_search 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 web_search 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 web_search. 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.
web_search is provided by the Wuxing Search MCP server (maeshughes/wuxing-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Wuxing Search MCP, 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 Wuxing Search MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.