Provides a tool to fetch web pages and convert their content into simplified Markdown, facilitating easier reading and processing of web-based information.
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., "@MCP Web Utilities Serversearch for the latest news on OpenAI and summarize the top result"
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 Utilities Server
Lightweight MCP server that exposes web search and page fetching tools.
Features
search_on_webandsearch_on_websiteusingddgs(DDGS | Dux Distributed Global Search, a multi-source search engine).fetch_webpagethat returns simplified Markdown usingcrawl4aiwith stealth settings.
Requirements
Python 3.13+
uvinstalled
Setup
Install uv on Windows (PowerShell):
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"uv syncThen activate the virtual environment and run the crawler setup:
.venv\Scripts\activate
crawl4ai-setupRun the server
uv run src\main.pyOr when developing:
start_mcp_server.cmdLM Studio Configuration
To use this server in LM Studio, add the following to your MCP settings (mcp.json):
{
"mcpServers": {
"web-utilities": {
"command": "uv",
"args": [
"--directory",
"D:\\Dev\\McpServer",
"run",
"src\\main.py"
]
}
}
}Note: Replace
Tools
search_on_web(query: str, results: int = 10) -> str
Returns results formatted as:
[title](url)
descriptionsearch_on_website(query: str, sites: list[str], results: int = 10) -> str
Same format, restricted to the provided
sites.
fetch_webpage(target_url: str) -> str
Returns simplified Markdown for the target page.
Tests
python -m unittest src.testsNotes
Avoid writing to
STDOUT(e.g.,print) when the server is running; it will break JSON RPC communication.Network-dependent tests may fail if external services are blocked in the current environment.