F
licenseNot graded
qualityD
maintenanceThis MCP server provides tools for AI agents to search the web, fetch page content, and query specific elements from pages using DuckDuckGo.
13 npm
-
DuckDuckGo Search MCP
by OEvortex
[!IMPORTANT] DuckDuckGo Search MCP 支持模型上下文协议 (MCP) 标准，使其与各种 AI 助手和工具兼容。
✨ 特点
[!IMPORTANT] 与许多搜索工具不同，此软件包执行实际的网络抓取而不是使用有限的 API，从而为您提供更全面的结果。
Related MCP server: webmcp
🚀 快速入门
npx -y @oevortex/ddg_search@latest[!TIP] 这将直接下载并运行最新版本的 MCP 服务器，无需安装 - 非常适合与 AI 助手快速使用。
🛠️ 安装选项
npm install -g @oevortex/ddg_search全局运行：
ddg-search-mcpgit clone https://github.com/OEvortex/ddg_search.git
cd ddg_search
npm install
npm start🧑💻 命令行选项
npx -y @oevortex/ddg_search@latest --help[!TIP] 使用 --version 标志检查您正在运行哪个版本。
🤖 与 MCP 客户端一起使用
[!IMPORTANT] 使用此工具最常见的方式是将其与 MCP 兼容的 AI 助手集成。
将服务器添加到您的 MCP 客户端配置：
{
"mcpServers": {
"ddg-search": {
"command": "npx",
"args": ["-y", "@oevortex/ddg_search@latest"]
}
}
}或者如果全局安装：
{
"mcpServers": {
"ddg-search": {
"command": "ddg-search-mcp"
}
}
}[!TIP] 配置完成后，重新启动 MCP 客户端以应用更改。
🧰 工具概述
📁 项目结构
bin/ # Command-line interface
src/
index.js # Main entry point
tools/ # Tool definitions and handlers
searchTool.js
fetchUrlTool.js
metadataTool.js
feloTool.js
utils/
search.js # Search and URL utilities
search_felo.js # Felo AI search utilities
package.json
README.md🤝 贡献
欢迎贡献！请打开问题或提交拉取请求。
[!NOTE] 请遵循现有的代码风格并为新功能添加测试。
📺 YouTube 频道
📄 许可证
Apache 许可证 2.0
[!NOTE] 该项目根据 Apache License 2.0 获得许可 - 有关详细信息，请参阅 LICENSE 文件。
Available Tools
1 toolweb-searchWeb SearchARead-only
Search the web. Use mode="web" for standard DuckDuckGo results (titles, URLs, snippets). Use mode="ai" for AI-generated answers — pick backend="iask" (default) or backend="monica".
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Search mode. "web" returns DuckDuckGo search results. "ai" returns an AI-generated answer. | web |
| query | Yes | The search query or question. | |
| backend | No | AI backend when mode="ai": "iask" or "monica". Ignored in web mode. | iask |
| iaskMode | No | IAsk mode when backend="iask": "question", "academic", "forums", "wiki", or "thinking". Default: "thinking". | thinking |
| numResults | No | Number of web results (1-20). Web mode only. Default: 3. | |
| detailLevel | No | IAsk detail level when backend="iask": "concise", "detailed", or "comprehensive". |
TDQS
A4.2/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the tool is inherently read-only. The description adds behavioral context: what each mode returns (titles/URLs/snippets vs. AI answer), default backends, and that mode can be chosen. No contradictions; description supplements annotations well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—two short sentences. It is front-loaded with the primary action and uses line breaks for readability. Every phrase adds value; no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately covers return types per mode. It mentions key parameters (mode, backend) but omits mentioning 'numResults' for web mode or 'iaskMode'/'detailLevel' for AI mode. However, since the schema provides full descriptions and the tool is simple, completeness is high but not perfect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds minimal parameter semantics beyond the schema, only noting the default value for 'backend'. It does not elaborate on 'numResults', 'iaskMode', or 'detailLevel', but the schema descriptions are already sufficient. Hence score 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Search the web.' It distinguishes two modes with specific outputs: 'mode="web" for standard DuckDuckGo results (titles, URLs, snippets)' and 'mode="ai" for AI-generated answers'. This provides a specific verb (search) and resource (web), and differentiates the major modes effectively.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use each mode: 'Use mode="web" for standard DuckDuckGo results' and 'Use mode="ai" for AI-generated answers'. It also provides guidance on backend selection for AI mode. With no sibling tools, no explicit when-not is necessary, but the guidance is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
3 tool updates
v1.4.0- Removed
iask-search - Removed
monica-search - Changed
web-search8 fields changed- added
Input schema / properties / backendAdded value: +{ + "default": "iask", + "description": "AI backend when mode=\"ai\": \"iask\" or \"monica\". Ignored in web mode.", + "enum": [ + "iask", + "monica" + ], + "type": "string" +} - added
Input schema / properties / detailLevelAdded value: +{ + "description": "IAsk detail level when backend=\"iask\": \"concise\", \"detailed\", or \"comprehensive\".", + "enum": [ + "concise", + "detailed", + "comprehensive" + ], + "type": "string" +} - added
Input schema / properties / iaskModeAdded value: +{ + "default": "thinking", + "description": "IAsk mode when backend=\"iask\": \"question\", \"academic\", \"forums\", \"wiki\", or \"thinking\". Default: \"thinking\".", + "enum": [ + "question", + "academic", + "forums", + "wiki", + "thinking" + ], + "type": "string" +} - changed
Input schema / properties / mode / defaultPrevious value: -"short"New value: +"web" - changed
Input schema / properties / mode / descriptionPrevious value: -"Choose 'short' for basic results (no Description) or 'detailed' for full results (includes Description)."New value: +"Search mode. \"web\" returns DuckDuckGo search results. \"ai\" returns an AI-generated answer." - changed
Input schema / properties / mode / enumPrevious value: -[ - "short", - "detailed" -]New value: +[ + "web", + "ai" +] - changed
Input schema / properties / numResults / descriptionPrevious value: -"Specify how many results to display (default: 3, maximum: 20)."New value: +"Number of web results (1-20). Web mode only. Default: 3." - changed
Input schema / properties / query / descriptionPrevious value: -"Enter your search query to find the most relevant web pages."New value: +"The search query or question."
6 tool updates
v1.0.0- Removed
felo-search - Removed
fetch-url - Added
iask-search - Added
monica-search - Removed
url-metadata - Changed
web-search5 fields changed- added
Input schema / properties / modeAdded value: +{ + "default": "short", + "description": "Choose 'short' for basic results (no Description) or 'detailed' for full results (includes Description).", + "enum": [ + "short", + "detailed" + ], + "type": "string" +} - changed
Input schema / properties / numResults / defaultPrevious value: -10New value: +3 - changed
Input schema / properties / numResults / descriptionPrevious value: -"Number of results to return (default: 10)"New value: +"Specify how many results to display (default: 3, maximum: 20)." - removed
Input schema / properties / pageRemoved value: -{ - "default": 1, - "description": "Page number (default: 1)", - "minimum": 1, - "type": "integer" -} - changed
Input schema / properties / query / descriptionPrevious value: -"The search query"New value: +"Enter your search query to find the most relevant web pages."
4 tool updates
- First observed
felo-search - First observed
fetch-url - First observed
url-metadata - First observed
web-search
TDQS
A4/5.0
Scored across 1 tool
Disambiguation5/5
Only one tool exists, so there is no possibility of confusion between tools. The two modes are clearly described within the single tool.
Naming Consistency5/5
With a single tool named 'web-search', the naming is self-consistent and follows a clear verb-noun pattern.
Tool Count2/5
A search server with only one tool feels too thin for the domain. Typically, separate tools for different search types (web, images, news, etc.) would be expected.
Completeness2/5
The single tool covers web and AI search but misses common search categories like images, news, and video, leaving notable gaps for typical search use cases.
Maintenance
ActivityInactive
ResponsivenessSlow
Related MCP Connectors
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Turn any public website into an MCP server for agents to search, read and navigate.
MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for web search and content extraction using DuckDuckGo or SearXNG, with Playwright-based fetching and LLM-powered data extraction.140MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for internet search via direct Google and DuckDuckGo HTML scraping with AI-powered result normalization and optional summarization, requiring no API keys for search.MIT
- FlicenseNot gradedqualityDmaintenanceMCP server that provides web search scraping from DuckDuckGo (with Mojeek fallback) and URL content fetching as markdown/text or raw HTML.1-
