Low Risk

search_api

根据 URL 模式搜索接口,这是查找接口的首选工具。 使用场景: - 当用户提到任何 API 路径或 URL 时,自动调用此工具查询 - 当用户询问某个功能的接口时,根据关键词搜索 - 当需要了解某个模块有哪些接口时 支持的匹配模式: - 精确匹配:/api/users - 通配符:/api/users/* 匹配所有子路径 - 模糊搜索:users、influencer 等关键词 - 路径片段:daren/influencer 匹配包含该片段的所有接口

How to control search_api ↓

What search_api does on Apifox Filter MCP Server

AI agents call search_api to retrieve information from Apifox Filter MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why search_api needs a policy

This is a read-only tool that retrieves and filters API documentation metadata from Apifox or OpenAPI sources. It supports various search patterns (exact, wildcard, fuzzy, fragment) to help locate endpoints, but performs no side effects. The context-reduction purpose and all sibling tools (list, batch_get, get_detail, refresh_cache) confirm this is a data retrieval utility with minimal risk.

From the tool's definition Tool description states it 'searches interfaces' and 'fetches API documentation' using URL patterns and keywords. The supported matching patterns (exact match, wildcard, fuzzy search, path fragment) all indicate query/retrieval operations.

Documented attack patterns abuse exactly the kind of access search_api gives an agent:

How to control search_api

PolicyLayer is an MCP gateway — it sits between your AI agents and Apifox Filter MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_api:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_api": {}
  }
}

search_api is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Apifox Filter MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about search_api

What does the search_api tool do? +

根据 URL 模式搜索接口,这是查找接口的首选工具。 使用场景: - 当用户提到任何 API 路径或 URL 时,自动调用此工具查询 - 当用户询问某个功能的接口时,根据关键词搜索 - 当需要了解某个模块有哪些接口时 支持的匹配模式: - 精确匹配:/api/users - 通配符:/api/users/* 匹配所有子路径 - 模糊搜索:users、influencer 等关键词 - 路径片段:daren/influencer 匹配包含该片段的所有接口. It is categorised as a Read tool in the Apifox Filter MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_api? +

Register the Apifox Filter MCP Server MCP server in PolicyLayer and add a rule for search_api: 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 Apifox Filter MCP Server. Nothing to install.

What risk level is search_api? +

search_api is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_api? +

Yes. Add a rate_limit block to the search_api 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.

How do I block search_api completely? +

Set action: deny in the PolicyLayer policy for search_api. 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.

What MCP server provides search_api? +

search_api is provided by the Apifox Filter MCP Server MCP server (xiaou66/apifox-filter-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Apifox Filter MCP Server tool call.

Start from Apifox Filter MCP Server, 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.

9 Apifox Filter MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.