F
licenseNot graded
qualityD
maintenanceMCP server that exposes web_search and web_fetch tools, allowing LLM applications to search the web via DuckDuckGo and fetch page content as cleaned markdown.
-
Web Search MCP Server
by sthbryan
Provides web search capabilities using DuckDuckGo as the primary search engine, with API and HTML scraping fallback.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Web Search MCP Serversearch for MCP protocol"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Web Search MCP Server
A Model Context Protocol server for web search and scraping using DuckDuckGo
Overview
This MCP server provides tools for AI agents to search the web, fetch page content, and query specific elements from pages. It uses DuckDuckGo as the primary search engine with a hybrid approach:
API search for fast, direct results
HTML scraping as fallback when API is unavailable
Native fetch for page retrieval and element queries
No headless browser or complex dependencies required.
Related MCP server: Internet Search MCP Server
Tools
search — Search DuckDuckGo
{ "query": "rust programming", "limit": 5 }Response:
{
"query": "rust programming language",
"source": "api",
"results": [
{ "title": "The Rust Programming Language", "url": "https://rust-lang.org" }
]
}fetch_page — Get page content (HTML/markdown/text)
{ "url": "https://example.com", "type": "markdown" }Response:
{
"url": "https://example.com",
"type": "markdown",
"source": "native",
"length": 1234,
"content": "# Example\n\nContent here..."
}query — Extract elements via CSS selector + text filter
{
"url": "https://example.com",
"selector": "h1, h2",
"text": "intro"
}Response:
{
"url": "https://example.com",
"source": "native",
"selector": "h1, h2",
"text": "intro",
"result": ["Introduction", "Getting Started"]
}Requirements
Node.js 18+ or Bun
Internet connection (for DuckDuckGo API/scraping)
Installation
# Clone and install dependencies
bun install
# Build for production
bun run buildAdd to your MCP servers config:
{
"mcpServers": {
"web-search": {
"command": "bunx",
"args": ["-y", "@sthbryan/web-search-mcp"]
}
}
}For client-specific configuration, see INSTALL.md.
Architecture
┌─────────────────────────────────────────────────────────────┐
│ MCP Client │
│ Coding Agent │
└─────────────────────────┬───────────────────────────────────┘
│ JSON-RPC
▼
┌─────────────────────────────────────────────────────────────┐
│ Web Search MCP Server │
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ │
│ │ search │ │ fetch │ │ query │ ← Tools │
│ └───┬─────┘ └───┬─────┘ └───┬─────┘ │
│ │ │ │ │
│ ▼ ▼ ▼ │
│ ┌─────────────────────────────────────────────────────────┐│
│ │ searchHandler() ││
│ │ (parallel API + scraping) ││
│ └──────────────────────────┬──────────────────────────────┘│
│ │ │
│ ┌────────────┴────────────┐ │
│ ▼ ▼ │
│ ┌────────────┐ ┌────────────┐ │
│ │ DuckDuckGo │ │ Native │ │
│ │ API │ │ fetch │ │
│ └────────────┘ └────────────┘ │
└─────────────────────────────────────────────────────────────┘How Search Works
User Query: "MCP protocol"
│
├─► DuckDuckGo API ──► Fast results
│ │
└─► DuckDuckGo Lite ──► HTML scraping
(on fallback) │
▼
┌────────────┐
│ Merge │
│ + Dedupe │
└────────────┘
│
▼
Final ResultsDevelopment
# Run in development mode
bun run dev
# Build for production
bun run build
# Type check
bun run checkLicense
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
ActivityInactive
ResponsivenessSyncing
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Scrape, crawl and search the web for AI agents via MCP.
MCP server for agentverse documentation, generated by doc2mcp.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceCustom MCP server exposing an internet_search tool that fetches DuckDuckGo results, enabling AI agents to perform web searches and retrieve structured information.1-
- FlicenseNot gradedqualityDmaintenanceMCP server that provides web search scraping from DuckDuckGo (with Mojeek fallback) and URL content fetching as markdown/text or raw HTML.1-
- AlicenseAqualityBmaintenanceMCP server for DuckDuckGo web search, enabling AI agents to perform real-time text, news, and image searches without an API key.3MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/sthbryan/web-search-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server