mcpField
M
Mcp Smartsearch

Mcp Smartsearch

Local
github.com/Cloudsway-AISearch0Updated 68w ago
Repository

About Mcp Smartsearch

Mcp Smartsearch is an MCP server for keyword-based web search through a remote search API. It returns structured JSON results and supports pagination, language, and safe-search options.

Key features

  1. 01Keyword-based web search
  2. 02Pagination controls
  3. 03Language selection
  4. 04Safe-search settings
  5. 05Structured JSON results

Use cases

  1. 01Search the web by keyword
  2. 02Retrieve results in pages
  3. 03Restrict search language or safety level

MCP support

Exposes the `smart_search` tool to MCP clients for web searches with query, count, offset, language, and safe-search parameters.

#mcp-smartsearch#web-search#api-integration

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "smartsearch": {
      "command": "uvx",
      "args": [
        "mcp-smartsearch"
      ],
      "env": {
        "SERVER_KEY": "<SERVER_KEY>"
      }
    }
  }
}
Run commanduvx mcp-smartsearch
Environment variables to set
SERVER_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-smartsearch

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Smart Search MCP Server

一个集成远程智能搜索 API 的 MCP 服务器，实现关键词网页搜索功能。

特性

  • 网页搜索：支持关键词检索、分页、语言和安全等级选项。
  • 结构化返回：所有搜索结果以 JSON 格式返回。
  • 平台兼容：为 ModelScope MCP 平台优化，支持从源码直接部署。

工具

smart_search
  • 功能: 执行网页搜索，支持分页与安全选项。
  • 输入参数:
    • query (string): 搜索关键词
    • count (number, optional): 返回结果数量 (默认 10)
    • offset (number, optional): 分页偏移 (默认 0)
    • setLang (string, optional): 搜索语言 (默认 'en')
    • safeSearch (string, optional): 安全搜索等级 (默认 'Strict')

配置与部署

1. 获取 API 密钥
  • 注册一个支持智能搜索的 API 服务。
  • 获取并复制你的 API 密钥（格式通常为 endpoint-apikey）。
2. ModelScope 服务配置

在 ModelScope 创建 MCP 服务时，请使用以下配置。这种方式会从你的 GitHub 仓库拉取代码，并直接运行。

{
  "mcpServers": {
    "mcp-smartsearch": {
      "command": "uvx",
      "args": [
        "mcp-smartsearch"
      ],
      "env": {
        "SERVER_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.