Web Search MCP Remote Server

Web Search MCP Remote Server

Remote HTTP/SSE MCP server for web search with full page content extraction, search summaries, and API authentication.

Category
Visit Server

README

Web Search MCP Remote Server

Remote HTTP/SSE MCP server for web search with full page content extraction, search summaries, and single page content extraction. Built on top of mrkrsl/web-search-mcp, extended with HTTP/SSE transport, API key authentication, and Docker deployment.

Features

  • Dual Transport: stdio (local) + HTTP/SSE (remote)
  • API Key Auth: secure remote access via SERVICE_API_KEY
  • Docker Ready: docker compose up for single-command deployment
  • Same Tools: full-web-search, get-web-search-summaries, get-single-web-page-content
  • Multi-Engine Search: Bing → Brave → DuckDuckGo
  • Full Content Extraction: concurrent page fetch with Playwright + axios fallback

Quick Start with Docker

# 1. Clone
git clone https://github.com/zerox2f/web-search-mcp-remote.git
cd web-search-mcp-remote

# 2. Create .env
echo "SERVICE_API_KEY=your-secret-key" > .env

# 3. Start
docker compose up --build

Server runs at http://127.0.0.1:3000 (health: /health, SSE: /mcp).

mcp.json Configuration for LLM Clients

HTTP/SSE (Remote / Docker)

{
  "mcpServers": {
    "web-search-remote": {
      "url": "http://127.0.0.1:3000/mcp",
      "transport": "sse",
      "headers": {
        "Authorization": "Bearer your-secret-key"
      }
    }
  }
}

stdio (Local)

{
  "mcpServers": {
    "web-search-local": {
      "command": "node",
      "args": ["/path/to/web-search-mcp-remote/dist/index.js"],
      "env": {
        "MAX_CONTENT_LENGTH": "50000",
        "BROWSER_HEADLESS": "true"
      }
    }
  }
}

Environment Variables

Variable Default Description
SERVICE_API_KEY (required in HTTP mode) API key for remote access
HOST 127.0.0.1 Bind address
PORT 3000 Server port
MAX_CONTENT_LENGTH 500000 Max chars per page
BROWSER_HEADLESS true Headless browser
MAX_BROWSERS 3 Browser pool size
DEFAULT_TIMEOUT 6000 Request timeout (ms)
BROWSER_FALLBACK_THRESHOLD 3 Axios failures before browser fallback

Project Structure

web-search-mcp-remote/
├── src/
│   ├── index.ts                  # stdio entry point + tool registration
│   ├── http-server-entry.ts      # HTTP/SSE entry point
│   ├── http-server.ts            # Express + SSEServerTransport
│   ├── auth.ts                   # API key middleware
│   ├── search-engine.ts          # Multi-engine search
│   ├── enhanced-content-extractor.ts
│   ├── browser-pool.ts
│   ├── types.ts
│   └── utils.ts
├── Dockerfile
├── docker-compose.yml
├── docs/DOCUMENTATION.md
└── PLAN.md

Development

# Install deps
npm install
npx playwright install

# Run stdio mode
npm run dev:stdio

# Run HTTP/SSE mode
SERVICE_API_KEY=secret npm run dev:remote

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured