Skip to main content
Glama

Web Search MCP Server

by vishalkg

Web Search MCP Server (Standalone)

A Model Context Protocol (MCP) server that provides web search capabilities using multiple search engines (DuckDuckGo, Bing, and Startpage) with parallel execution and result deduplication.

Features

  • Multi-engine search: Searches DuckDuckGo, Bing, and Startpage simultaneously
  • Parallel execution: All searches run concurrently for faster results
  • Result deduplication: Removes duplicate URLs from combined results
  • Source attribution: Shows which search engine provided each result
  • Comprehensive logging: Logs all operations to web-search.log
  • Standalone: Pre-configured virtual environment included - no setup required
  • Two tools available:
    • SearchWeb: Multi-engine web search
    • FetchPageContent: Extract text content from web pages

Installation

Option 1: Standalone (Pre-configured venv included)

  1. Extract the files:
    unzip web-search-mcp.zip -d ~/.mcp/
  2. Make start script executable:
    chmod +x ~/.mcp/web-search/start.sh
  3. Add to Q CLI MCP configuration:
    q mcp add web-search ~/.mcp/web-search/start.sh
  4. Verify installation and test:
    q mcp status --name web-search q chat # In chat: "search web for python libraries"

Option 2: Manual Setup (If venv is missing)

  1. Navigate to the directory:
    cd ~/.mcp/web-search
  2. Create virtual environment:
    python3 -m venv venv
  3. Activate virtual environment and install dependencies:
    source venv/bin/activate pip install -r requirements.txt deactivate
  4. Make start script executable:
    chmod +x start.sh
  5. Add to Q CLI MCP configuration:
    q mcp add web-search ~/.mcp/web-search/start.sh
  6. Test the installation:
    q mcp status --name web-search

Files Included

  • server.py - Main MCP server code
  • start.sh - Startup script
  • requirements.txt - Python dependencies
  • venv/ - Pre-configured virtual environment with all dependencies
  • README.md - This documentation

Usage

Start a new Q CLI chat session. The server provides two tools:

SearchWeb

Search query: "python web scraping libraries"

FetchPageContent

Fetch content from: "https://example.com"

Logs

All operations are logged to web-search.log in the server directory with timestamps and detailed information about search requests and results.

Troubleshooting

  • Permission denied: Ensure start.sh is executable (chmod +x start.sh)
  • No search results: Check the log file for error messages
  • Debugging: Check web-search.log for detailed debugging information

Requirements

  • Q CLI with MCP support
  • Internet connection for web searches
  • macOS/Linux (Python 3.11+ included in venv)
-
security - not tested
F
license - not found
-
quality - not tested

local-only server

The server can only run on the client's local machine because it depends on local resources.

Enables web search across multiple search engines (DuckDuckGo, Bing, Startpage) with parallel execution and result deduplication. Also provides web page content extraction capabilities.

  1. Features
    1. Installation
      1. Option 1: Standalone (Pre-configured venv included)
      2. Option 2: Manual Setup (If venv is missing)
    2. Files Included
      1. Usage
        1. SearchWeb
        2. FetchPageContent
      2. Logs
        1. Troubleshooting
          1. Requirements

            MCP directory API

            We provide all the information about MCP servers via our MCP API.

            curl -X GET 'https://glama.ai/api/mcp/v1/servers/vishalkg/web-search'

            If you have feedback or need assistance with the MCP directory API, please join our Discord server