Orz Mcp
by
Provides web_search and web_fetch capabilities via an MCP server, enabling AI assistants to query the internet and retrieve page content, with optional Google Gemini search and proxy support.
Orz Mcp Overview
What is Orz Mcp about?
Enables AI assistants such as Claude, Cursor, and OpenCode to perform internet searches and fetch web pages. It aggregates results from DuckDuckGo and, when a Gemini API key is supplied, from Google Search Grounding, then returns clean, de‑duplicated results. Fetching converts HTML to Markdown and respects size limits and timeouts.
How to use Orz Mcp?
- StdIO mode (local): Run the server directly with
npx. Example configuration for an MCP client:
{
"mcpServers": {
"orz": {
"type": "stdio",
"command": "npx",
"args": ["-y", "orz-mcp", "--gemini-api-key", "YOUR_KEY", "--proxy", "http://user:pass@proxy-host:port"]
}
}
}
Use the --gemini-api-key flag or set GEMINI_API_KEY in the environment to enable Google search. Proxy can be supplied via --proxy or the PROXY_URL environment variable.
- Streamable HTTP mode (cloud): Deploy the
streamable-httpfolder to Netlify (or similar) and point the client to the endpoint:
{
"mcpServers": {
"orz": {
"type": "http",
"url": "https://<your-netlify-domain>/mcp"
}
}
}
Environment variables such as GEMINI_API_KEY and PROXY_URL can be set in the Netlify dashboard.
Key Features
- Concurrent DuckDuckGo search with automatic de‑duplication and ad filtering.
- Optional Google Search Grounding via Gemini API (5000 free queries per month).
- Configurable result count (
num_results, default 8). - Web fetch that returns plain‑text Markdown, configurable max characters and simplification flag.
- Built‑in 10‑second fetch timeout.
- Proxy support via command‑line
--proxyorPROXY_URLenv variable. - Two transport protocols: stdio (Node.js) and HTTP (Netlify Functions) with identical toolsets.
Use Cases
- Augmenting conversational AI with up‑to‑date web information.
- Automated research assistants that gather links, titles, summaries, and page content.
- Content summarization pipelines that need raw Markdown from articles.
- Building custom chat‑bots that can browse the web, cite sources, and answer fact‑based queries.
- Integrating search and fetch capabilities into internal tools without exposing full browsers.
FAQ
- Do I need a Gemini API key? Only if you want Google search; DuckDuckGo works without any key.
- How many results can I request?
num_resultsdefaults to 8; you can request up to the service limits. - Can I use a proxy? Yes, via
--proxy http://host:port(stdio) or thePROXY_URLenvironment variable (HTTP mode). - What is the maximum size of fetched content? Default is 50,000 characters; adjust with
max_char_size. - How do I deploy the HTTP version? Use Netlify CLI:
netlify initthennetlify deploy --prod, or connect the GitHub repo to Netlify for automatic deploys.
Orz Mcp's README
ORZ MCP
一个提供 web_search 和 web_fetch 能力的 MCP (Model Context Protocol) 服务器。
让你的 AI 助手（Claude、Cursor、OpenCode 等）能够搜索互联网和抓取网页内容。
功能
web_search
并发查询 DuckDuckGo（及配置 Key 时开启的 Google）搜索引擎，自动合并去重、过滤广告。
- 入参:
query（搜索关键词）、num_results（返回数量，默认 8） - 返回:
{ url, title, summary }[] - Google 搜索（官方 Grounding）：
- 配置
GEMINI_API_KEY（或--gemini-api-key），直接调用 Google 官方 Gemini API 的 Google Search Grounding（每月拥有 5000 次免费额度，官方实时数据，不惧爬虫风控）。未配置时默认只运行 DuckDuckGo。详细开启步骤见下方 Google Search 配置指南。
- 配置
Google Search 配置指南
1. 获取 Gemini API Key
- 访问 Google AI Studio。
- 点击 Create API Key 创建你的 API Key。
- 免费额度与计费说明：Google Search Grounding 要求绑定结算账户（开启 Pay-as-you-go / Tier 1）。绑定后每月享有前 5,000 次免费查询（查询计费为 14 / 1,000 次计费（详见 Gemini API 官方定价）。未绑定结算账户的项目无法调用 Grounding 搜索。
2. 如何开启
- stdio（本地使用）：
- 方式 A（推荐，命令行参数）：通过
--gemini-api-key <YOUR_KEY>传入。 - 方式 B（环境变量）：在配置文件的
env中设置GEMINI_API_KEY。
- 方式 A（推荐，命令行参数）：通过
- Streamable HTTP（云端 Netlify / Railway 部署）：
- 在云平台的控制台环境变量（Environment Variables）中添加
GEMINI_API_KEY=<YOUR_KEY>即可自动生效。
- 在云平台的控制台环境变量（Environment Variables）中添加
web_fetch
抓取指定 URL 的网页内容，默认简化为 Markdown 格式。
- 入参:
url、max_char_size（最大字符数，默认 50000）、simplify（是否简化，默认 true） - 返回: 纯文本字符串（Markdown 格式）
- 内置 10 秒超时
两种使用方式（二选一）
ORZ MCP 提供 stdio 和 Streamable HTTP 两种 MCP 传输协议的实现，功能完全一致，根据你的需求选择其中一种即可。
| stdio | Streamable HTTP | |
|---|---|---|
| 运行方式 | 通过 npx 本地启动 | 远程 HTTP 服务（Netlify Functions） |
| 适用场景 | 本地运行，支持代理与 API Key | 开箱即用，支持云端部署、住宅代理与 API Key |
| 代理支持 | 支持 --proxy 命令行参数与环境变量 |
支持环境变量 PROXY_URL（如住宅 IP 代理） |
| 依赖 | Node.js >= 18 | 无 |
方式一：stdio（通过 npx 本地运行）
无需安装，直接通过 npx 运行。
在你的 MCP 客户端配置中添加：
1. 开启 Gemini 官方 Google Search（推荐）：
使用命令行参数：
{
"mcpServers": {
"orz": {
"type": "stdio",
"command": "npx",
"args": ["-y", "orz-mcp", "--gemini-api-key", "AIzaSy..."]
}
}
}
或者使用环境变量：
{
"mcpServers": {
"orz": {
"type": "stdio",
"command": "npx",
"args": ["-y", "orz-mcp"],
"env": {
"GEMINI_API_KEY": "AIzaSy..."
}
}
}
}
2. 配置住宅代理（或科学上网代理）：
{
"mcpServers": {
"orz": {
"type": "stdio",
"command": "npx",
"args": ["-y", "orz-mcp", "--proxy", "http://user:pass@proxy-host:port"]
}
}
}
也可以两者同时使用（--gemini-api-key + --proxy）。
方式二：Streamable HTTP（远程连接）
无需本地安装任何东西，直接连接部署在 Netlify 上的远程服务。
{
"mcpServers": {
"orz": {
"type": "http",
"url": "https://<your-netlify-domain>/mcp"
}
}
}
如果你的 MCP 客户端不支持直接 URL 连接，可以通过 mcp-remote 桥接：
{
"mcpServers": {
"orz": {
"command": "npx",
"args": ["mcp-remote@next", "https://<your-netlify-domain>/mcp"]
}
}
}
配置文件位置
不同的 MCP 客户端配置文件位置不同：
- Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json(macOS) - Cursor: Settings > MCP Servers
- OpenCode:
.opencode/config.json或通过/mcp命令添加
项目结构
orz-mcp/
├── stdio/ # stdio 传输协议 (npm 包)
│ ├── client.mjs # 入口文件
│ └── package.json # npm 发布配置（依赖: mcp sdk, turndown, undici）
├── streamable-http/ # Streamable HTTP 传输协议 (Netlify Functions)
│ ├── netlify/
│ │ ├── mcp-server/
│ │ │ └── index.ts # MCP Server 定义（工具注册与业务逻辑）
│ │ └── functions/
│ │ └── hono-mcp-server.ts # Hono HTTP handler (Netlify Function)
│ ├── public/
│ │ └── index.html # 静态首页
│ ├── netlify.toml # Netlify 构建配置
│ └── package.json # 服务端依赖（依赖: mcp sdk, hono, zod, turndown）
└── README.md
开发
stdio
cd stdio
npm install
node client.mjs
node client.mjs --proxy http://127.0.0.1:7890
node client.mjs --help
# 用 MCP Inspector 调试
npx @modelcontextprotocol/inspector node client.mjs
Streamable HTTP（本地调试）
cd streamable-http
npm install
# 启动本地开发服务器（需要 Netlify CLI）
netlify dev
# 用 MCP Inspector 测试（在 UI 中选择 Streamable HTTP，填入 URL）
npx @modelcontextprotocol/inspector --url http://localhost:8888/mcp
部署到 Netlify
cd streamable-http
# 安装 Netlify CLI
npm install -g netlify-cli
# 登录
netlify login
# 初始化并关联站点
netlify init
# 部署
netlify deploy --prod
或者通过 GitHub 连接 Netlify，push 到 main 分支自动部署。
License
MIT
Orz Mcp Reviews
Login Required
Please log in to share your review and rating for this MCP.
Similar MCP Servers like Orz Mcp
Explore related MCPs that share similar capabilities and solve comparable challenges
Exa MCP Server
Officialby exa-labs
Provides real-time web search capabilities to AI assistants via a Model Context Protocol server, enabling safe and controlled access to the Exa AI Search API.
Perplexity Ask
Officialby perplexityai
Enables Claude and other MCP‑compatible applications to perform real‑time web searches through the Perplexity (Sonar) API without leaving the MCP ecosystem.
Open WebSearch
by Aas-ee
Provides multi-engine web search and article/content retrieval through an MCP server, command‑line interface, and a reusable local daemon, all without requiring API keys or authentication.
Microsoft Learn MCP Server
by MicrosoftDocs
Provides semantic search and fetch capabilities for Microsoft official documentation, returning content in markdown format via a lightweight streamable HTTP transport for AI agents and development tools.
Elasticsearch MCP Server
by elastic
Enables natural‑language interaction with Elasticsearch indices via the Model Context Protocol, exposing tools for listing indices, fetching mappings, performing searches, running ES|QL queries, and retrieving shard information.
Graphlit MCP Server
by graphlit
Enables integration between MCP clients and the Graphlit platform, providing ingestion, extraction, retrieval, and RAG capabilities across a wide range of data sources and connectors.
SearXNG MCP Server
by ihor-sokoliuk
Provides web search capabilities via the SearXNG API, exposing them through an MCP server for seamless integration with AI agents and tools.
Everything Search
by mamertofabian
Fast cross‑platform file searching leveraging the Everything SDK on Windows, Spotlight on macOS, and locate/plocate on Linux.
Mcp Omnisearch
by spences10
Provides unified access to multiple search engines, AI response tools, and content processing services through a single Model Context Protocol server.