JoaoPedroLanca/mcp-web-tools
If you are the rightful owner of mcp-web-tools and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
The MCP Web Tools Server is a Node.js-based server designed to enhance internet connectivity for LM Studio through the Model Context Protocol.
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 install
Execution (stdio mode)
npm start
The 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)
- input:
-
fetch_url:- input:
{ "url": string, "maxBytes?": number (up to 8MB) } - output: two text blocks: metadata (contentType/bytes) and truncated body
- input:
-
extract_readable:- input:
{ "url": string } - output: text with title, byline, summary and main content
- input:
Getting Started
Clone the repository:
git clone https://github.com/JoaoPedroLanca/mcp-web-tools.git
cd mcp-web-tools
npm install
npm start
Notes
- 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.