MCP.so
Sign In

WebSearch-MCP

@mnhlt

About WebSearch-MCP

[Self-hosted] A Model Context Protocol (MCP) server implementation that provides a web search capability over stdio transport. This server integrates with a WebSearch Crawler API to retrieve search results.

Basic information

Category

Search

Runtime

node

Transports

stdio

Publisher

mnhlt

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "websearch": {
      "command": "npx",
      "args": [
        "websearch-mcp"
      ],
      "environment": {
        "API_URL": "http://localhost:3001",
        "MAX_SEARCH_RESULT": "5"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is WebSearch-MCP?

WebSearch-MCP is a Model Context Protocol server that provides web search capabilities to AI assistants. It integrates with a WebSearch Crawler API to retrieve real-time search results and communicates with AI models over stdio transport.

How to use WebSearch-MCP?

Install the server via Smithery or npm, then run npx websearch-mcp. Configure the crawler API endpoint and maximum results via the API_URL and MAX_SEARCH_RESULT environment variables. The server exposes a web_search tool that can be called from any MCP-compatible client.

Key features of WebSearch-MCP

  • Provides a web_search tool with customizable parameters.
  • Supports filtering by language, region, domain inclusion/exclusion.
  • Returns structured results (title, snippet, URL, site name, byline).
  • Uses stdio transport for MCP communication.
  • Configurable via environment variables (API_URL, MAX_SEARCH_RESULT).
  • Integrates with a Docker-based crawler service using Flaresolverr.

Use cases of WebSearch-MCP

  • AI assistants can search the web in real-time during conversations.
  • Obtain up-to-date information on topics like trends, news

Comments

More Search MCP servers