The DuckDuckGo Search MCP is a privacy-friendly server implementation of the Model Context Protocol (MCP) that enables web search and URL content extraction. It provides AI assistants with the ability to search the web and extract content from websites without requiring API keys.
You can instantly run the MCP server using npx without installation:
npx -y @oevortex/ddg_search
This downloads and runs the server directly - perfect for quick use with AI assistants.
npm install -g @oevortex/ddg_search
After installing globally, you can run it using:
ddg-search-mcp
git clone https://github.com/OEvortex/ddg_search.git
cd ddg_search
npm install
npm start
You can view available command-line options by running:
npx -y @oevortex/ddg_search --help
To check which version you're running:
npx -y @oevortex/ddg_search --version
The most common way to use this tool is by integrating it with MCP-compatible AI assistants.
Add the server to your MCP client configuration:
{
"mcpServers": {
"ddg-search": {
"command": "npx",
"args": ["-y", "@oevortex/ddg_search"]
}
}
}
Or if installed globally:
{
"mcpServers": {
"ddg-search": {
"command": "ddg-search-mcp"
}
}
}
After configuring, restart your MCP client to apply the changes.
This tool allows you to search the web using DuckDuckGo.
web-search
query
(string, required): The search querypage
(integer, optional, default: 1): Page numbernumResults
(integer, optional, default: 10): Number of results (1-20)Example use case: Search the web for "climate change solutions"
This tool extracts content from a specified URL.
fetch-url
url
(string, required): The URL to fetchmaxLength
(integer, optional, default: 10000): Max content lengthextractMainContent
(boolean, optional, default: true): Extract main contentincludeLinks
(boolean, optional, default: true): Include link textincludeImages
(boolean, optional, default: true): Include image alt textexcludeTags
(array, optional): Tags to excludeExample use case: Fetch the content from "https://example.com"
This tool extracts metadata from a specified URL.
url-metadata
url
(string, required): The URL to extract metadata fromExample use case: Get metadata for "https://example.com"
Unlike many search tools, this package performs actual web scraping rather than using limited APIs, giving you more comprehensive results.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.