MCP Web Tools Server
Enables web search functionality using DuckDuckGo's HTML interface without requiring an API key, returning search results with titles and URLs.
Provides web search capabilities through SerpAPI's Google search integration when an API key is configured, returning search results with titles and URLs.
Click on "Deploy 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., "@MCP Web Tools Server search for latest AI developments"
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.
MCP Web Tools Server (Node.js)
⭐ If you find this useful, please consider giving it a star!
MCP (Model Context Protocol) server for LM Studio that provides tools for internet connectivity:
search_web: searches the web and returns titles and URLs
fetch_url: performs HTTP GET and returns content-type and body (limited)
extract_readable: extracts the main readable content from a page
Requirements
Node.js 18+
Installation
npm installExecution (stdio mode)
npm startThe server uses stdio (required for integration with LM Studio via MCP).
Environment variables (optional)
SERPAPI_KEY: if provided, thesearch_webtool will use SerpAPI (Google). Otherwise, leave the field empty to use DuckDuckGo (HTML) without a key.
LM Studio Configuration
Add a custom MCP server pointing to this project's command. In LM Studio, go to Program → Install → Edit mcp.json, and paste the json below:
{
"mcpServers": {
"mcp-web-tools-server": {
"command": "npm",
"args": [
"run",
"start",
"--silent"
],
"cwd": "C:/mcp-web-tools",
"env": {
"SERPAPI_KEY": ""
}
}
}
}In "cwd" put the project Path
Available tools
search_web:input:
{ "query": string, "limit?": number (1..10) }output: text with numbered list (title and URL)
fetch_url:input:
{ "url": string, "maxBytes?": number (up to 8MB) }output: two text blocks: metadata (contentType/bytes) and truncated body
extract_readable:input:
{ "url": string }output: text with title, byline, summary and main content
Getting Started
Clone the repository:
git clone https://github.com/JoaoPedroLanca/mcp-web-tools.git
cd mcp-web-tools
npm install
npm startNotes
Very large responses are truncated (16MB by default) to avoid exceeding client limits.
search_webwithout a key uses DuckDuckGo HTML; results may vary and are subject to site changes.
Available Tools
3 toolsextract_readableD
Inputs: url (required).
fetch_urlD
Inputs: url (required), maxBytes.
search_webD
Inputs: query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The tools have distinct primary actions (extract, fetch, search), but without descriptions, their exact scopes and potential overlaps are unclear. An agent might confuse when to use fetch_url versus search_web if both involve web retrieval, but the verb differences provide some guidance.
All tool names follow a consistent verb_noun pattern with snake_case (extract_readable, fetch_url, search_web), making them predictable and readable. There are no deviations in naming style across the set.
With only 3 tools, the set feels thin for a 'Web Tools Server', suggesting it might lack coverage for common web operations like parsing or interacting with content. However, the count is not extreme and could be appropriate if these are core utilities.
Inferred domain is web-related utilities, but the surface is severely incomplete: missing obvious tools for actions like parsing HTML, handling cookies, or managing sessions. The three tools provide basic fetch, extract, and search functions, but leave significant gaps for comprehensive web tooling.
Maintenance
Related MCP Connectors
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Web search and page reading for AI agents, including JSON APIs, RSS feeds and YouTube.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables web searching through DuckDuckGo and fetching content from webpages. Provides search capabilities with configurable result limits and webpage content extraction for AI assistants.-
- AlicenseBqualityDmaintenanceEnables web search through DuckDuckGo and webpage content fetching with intelligent text extraction. Features built-in rate limiting and LLM-optimized result formatting for seamless integration with language models.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables web searching through Google, DuckDuckGo, and Bing using a headless Chrome browser, returning structured results with titles, URLs, and snippets. Also supports fetching and extracting text content from any webpage.16MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search the internet using DuckDuckGo and extract clean, formatted content from web pages.121 npmGPL 3.0