Provides web search capabilities through DuckDuckGo's search engine, allowing queries with configurable result limits.
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 Neosearch DuckDuckGo for latest AI news and fetch 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.
Web search Neo
Python URL fetcher with MCP‑based tools for fetching URLs, extracting text, and web searching.
Installation
Running the MCP Server
The server exposes the following tools via the MCP protocol:
fetch_url_text(url)– get plain text from a URL.fetch_page_links(url)– list links on a page.search_duckduckgo(query, num)– DuckDuckGo search.search_yandex(query, num)– Yandex search.get_current_time_and_region()– local date/time.
CLI Usage
Logs are written to msp_server.log.
MCP API Example
Example Configuration (msp.json)
A sample configuration file msp.json can be used to customize the MCP server:
Place this file in the project root to customize server settings.
Contributing
Fork, pull requests, issues. Follow style and tests.