searchLABSCO SUMMARY
Free search, with the trade-off scraping always carries.
Every other search server wants an API key and a billing account; this one wants neither, and the structured title/URL/description shape is exactly what a model needs to decide what to open next. The trade-off is inherent to scraping — no service agreement behind it and a hard ceiling of 10 results — so treat it as a personal-use tool rather than something to put under a product.
What it is
A single-tool search server that returns DuckDuckGo results. There is no key to obtain and no account to create: build it, point your client at the binary, and search calls start working.
What you get
searchtakes aquerystring and an optionallimitlimitdefaults to 5 results and accepts up to 10- Structured results — each one a title, a URL and a description
- No API key or authentication anywhere in the path
Requirements
Node. Clone the repository, npm install, npm run build, then run build/index.js under node — setup snippets are given for Claude Desktop and for the Claude Dev extension in VSCode. No credentials. Results are scraped from the search page rather than fetched through an API, and the author positions this for personal use. Version 0.1.0.
Setup effort
Build from source
USE CASES
01
Giving an assistant a way to look things up
Add one search tool with no signup step in the way.
02
Finding a page to read in full
Get back titles, URLs and descriptions, then fetch the one that matters.
03
Keeping search results short
Set limit to 3 so a lookup does not fill the context with ten summaries.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation. The documentation conflicts on the engine: it promises DuckDuckGo with no API key, but also says it scrapes Google search results.
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/sam2332/mcp-web-search
cd mcp-web-search
npm install
npm run buildMCP Clients
Claude Dev, Claude Desktop
JSON
{
"mcpServers": {
"web-search": {
"command": "node",
"args": [
"<YOUR_PATH_TO_WEB_SEARCH>/build/index.js"
]
}
}
}
