Multi-Provider Web Search Server provides unified access to multiple search engines through a single interface, automatically managing provider fallback to maximize available search quotas. Key features: - Integrates with four major search providers: Google Custom Search, Tavily, DuckDuckGo, and Brave Search. - Implements intelligent priority-based fallback (default: Tavily → Google → DuckDuckGo → Brave) when providers reach quota limits or fail. - Exposes a single standardized `search` tool that returns consistent result formats regardless of the underlying provider. - Supports direct provider specification for targeted searches or automatic selection based on availability. - Configurable via environment variables for API keys and preferences.

MCP Search Server

[](https://smithery.ai/server/@guptabhishek/multi-search-mcp)

This package exists to provide a unified MCP (Model Context Protocol) interface for multi-provider web search. It allows you to leverage the free monthly quota given by multiple search services (such as Google and Tavily) by automatically falling back between them, maximizing your available search capacity for automation and AI workflows.

Features

Getting Free API Credentials

Tavily

1. Go to Tavily and sign up for a free account. 2. After verifying your email, log in to your Tavily dashboard. 3. Navigate to the API section and generate a free API key. 4. Copy the API key and use it as TAVILY_API_KEY in your configuration.

Brave Search

1. Go to Brave Search API and click "Get started". 2. Sign in or create a Brave account. 3. Follow the instructions to subscribe to the Brave Search API (free tier available). 4. Once subscribed, go to your Brave dashboard and generate an API key. 5. Copy the API key and use it as BRAVE_API_KEY in your MCP client configuration (must be passed via MCP env, not .env).

Google Custom Search

1. Go to the Google Cloud Console and create a new project (or select an existing one). 2. Enable the Custom Search API for your project. 3. Go to the Custom Search Engine and create a new search engine. - For "Sites to search", you can enter www.example.com (you can edit this later to search the entire web). - After creation, go to the control panel of your search engine and enable "Search the entire web" in the "Sites to search" section. 4. Copy the Search Engine ID (CX) and use it as GOOGLE_CX. 5. In the Cloud Console, go to APIs & Services > Credentials and create an API key. 6. Use this API key as GOOGLE_API_KEY in your configuration.

Setup

Installing via Smithery

To install multi-search-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @guptabhishek/multi-search-mcp --client claude

Installing Manually

npm run build
npm start

1. Clone/Download: Get the server code. 2. Install Dependencies:

    npm install
    

    {
      "servers": {
        // ... other servers ...
        "search": { // Or your chosen name for this server
          "autoApprove": [],
          "disabled": false, // Set to false to enable
          "timeout": 120,
          "command": "npx", // Or the command to run the server
          "args": [
              "-y",
              "mcp-search-server"
          ],
          "env": {
            // Required API Keys
            "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY",
            "GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY",
            "GOOGLE_CX": "YOUR_GOOGLE_CUSTOM_SEARCH_ENGINE_ID",
            "BRAVE_API_KEY": "YOUR_BRAVE_SEARCH_API_KEY", // Brave Search API Key (must be passed via MCP env, not .env)
            // DuckDuckGo does not require an API key.
            // Optional: Configure providers and strategy
            "SEARCH_PROVIDERS": "tavily,google,duckduckgo,brave", // Comma-separated list of providers in desired priority
            "SEARCH_STRATEGY": "random", // Or "priority"
            // Optional Port Override
            "PORT": "3002" // Example: run on port 3002 instead of default
          },
          "transportType": "stdio" // Assuming stdio transport
        }
        // ... other servers ...
      }
    }
    

Running the Server

npm start

The server will start, typically on port 3001 (or the port specified in .env). It will print the available tool name and the status of loaded API keys