Skip to main content
Glama
Sign In
deenesjakoruzh
mcp-web-search

mcp-web-search

by doranobik
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

MCP Web Search

A Model Context Protocol (MCP) server for web search using DuckDuckGo. No API key required.

Features

  • Web Search - Search the web via DuckDuckGo's static HTML interface

  • Content Extraction - Fetch and extract readable content from any webpage using Mozilla's Readability

  • Zero Configuration - No API keys, no signup, works out of the box

  • Lightweight - Uses Node.js native fetch, no heavy browser automation

Related MCP server: Web Scout MCP Server

Tools

Tool

Description

webSearch

Search the web with DuckDuckGo. Returns title, URL, and snippet for each result.

fetchWebContent

Extract main text content from a webpage URL. Removes ads, navigation, and noise.

Usage

Local installation

git clone https://github.com/doranobik/mcp-web-search.git
cd mcp-web-search
npm install
npm run build
node dist/index.js

Note: This package is not published to npm. The mcp-web-search name on npm belongs to an unrelated project, so install from this repository instead.

Docker

docker build -t mcp-web-search .
docker run -i mcp-web-search

MCP Client Configuration

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "web-search": {
      "command": "node",
      "args": ["/path/to/mcp-web-search/dist/index.js"]
    }
  }
}

LM Studio (mcp.json):

{
  "mcpServers": {
    "web-search": {
      "command": "node",
      "args": ["/path/to/mcp-web-search/dist/index.js"]
    }
  }
}

Tool Parameters

webSearch

Parameter

Type

Required

Default

Description

query

string

Yes

-

Search query

maxResults

number

No

10

Max results (1-20)

region

string

No

-

Region code (e.g., jp-ja, us-en, wt-wt)

fetchWebContent

Parameter

Type

Required

Default

Description

url

string

Yes

-

URL to fetch

maxChars

number

No

5000

Max characters to return (100-200000)

Disclaimer

This server searches the web by parsing DuckDuckGo's HTML interface, not an official API. It may break if DuckDuckGo changes its markup, and heavy automated use may violate DuckDuckGo's terms of service or lead to rate limiting. Use it responsibly and at your own risk.

License

MIT — see LICENSE for details.

Available Tools

2 tools
fetchWebContentFetch Web ContentA

<use_case>Fetch and extract the main text content from a webpage. Use this tool after webSearch to read the full content of a specific URL, or when given a direct URL to analyze.</use_case> <important_notes>

  • Extracts readable article text, removing ads, navigation, and other non-content elements

  • Works best with article pages, blog posts, and documentation

  • May not work well with heavily JavaScript-rendered pages or pages requiring login

  • Use maxChars to limit returned content length for large pages </important_notes>

Inputs: url (required), maxChars.

webSearchWeb SearchA

<use_case>Search the web using DuckDuckGo. Use this tool when you need to find current information, news, documentation, or answers to questions from the internet.</use_case> <important_notes>

  • No API key required

  • Results include title, URL, and snippet for each result

  • Use the region parameter to get localized results (e.g., 'jp-ja' for Japanese)

  • After getting search results, use fetchWebContent to read full page content from any URL </important_notes>

Inputs: query (required), region, maxResults.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.5/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: webSearch for querying the web and fetchWebContent for retrieving page content. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    Both tool names follow a consistent camelCase verb-noun pattern (webSearch, fetchWebContent), making them predictable and easy to understand.

    Tool Count4/5

    With only 2 tools, the server is minimal but well-scoped for its stated purpose of web search and content fetching. While the typical range is 3-15, this lean set is appropriate for the narrow domain.

    Completeness5/5

    The server covers the essential workflow of searching the web and then fetching full content from selected URLs. No critical operations are missing for its intended use case.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers