Question 1

What is an MCP Server?

Accepted Answer

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. An MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools.

Question 2

What is the `ddg-mcp` MCP Server?

Accepted Answer

The `ddg-mcp` MCP server provides DuckDuckGo search capabilities through the Model Context Protocol. It allows AI agents to perform web searches, image searches, news searches, video searches, and even chat with DuckDuckGo AI.

Question 3

What are the prerequisites for installing the `ddg-mcp` server?

Accepted Answer

You need Python 3.9 or higher and either `uv` (recommended) or `pip` package manager.

Question 4

How do I install the `ddg-mcp` server?

Accepted Answer

You can install it from PyPI using `uv install ddg-mcp` or `pip install ddg-mcp`. Alternatively, you can install it from source by cloning the repository and running `uv install -e .` or `pip install -e .`.

Question 5

What dependencies are required?

Accepted Answer

The server requires the `duckduckgo-search` package, which is installed automatically when you install `ddg-mcp`. If you need to install it manually, use `uv install duckduckgo-search` or `pip install duckduckgo-search`.

Question 6

How do I configure the server?

Accepted Answer

The server can be configured using command-line arguments. For example, you can specify the transport protocol (`--transport stdio` for stdio transport) and the host and port for SSE transport (`--host 0.0.0.0 --port 3001`).

Question 7

What search parameters can I use?

Accepted Answer

You can use common parameters like `region`, `safesearch`, `timelimit`, and `max_results` for most search types. There are also specific parameters for image and video searches, such as `size`, `color`, `type_image`, `layout`, and `license_image` for images, and `resolution`, `duration`, and `license_videos` for videos.

Question 8

What are the available AI Chat models?

Accepted Answer

The server supports several AI models, including `gpt-4o-mini`, `llama-3.3-70b`, `claude-3-haiku`, `o3-mini`, and `mistral-small-3`.

Question 9

How do I use the `ddg-text-search` tool?

Accepted Answer

Use the `ddg-text-search` tool with the `keywords` argument to specify the search query. You can also use optional parameters like `region`, `safesearch`, `timelimit`, and `max_results`.

Question 10

How do I use the `ddg-image-search` tool?

Accepted Answer

Use the `ddg-image-search` tool with the `keywords` argument to search for images. You can also use optional parameters like `size`, `color`, `type_image`, `layout`, and `license_image`.

Question 11

How do I use the `ddg-news-search` tool?

Accepted Answer

Use the `ddg-news-search` tool with the `keywords` argument to search for news articles. You can also use optional parameters like `region`, `safesearch`, and `timelimit`.

Question 12

How do I use the `ddg-video-search` tool?

Accepted Answer

Use the `ddg-video-search` tool with the `keywords` argument to search for videos. You can also use optional parameters like `resolution`, `duration`, and `license_videos`.

Question 13

How do I use the `ddg-ai-chat` tool?

Accepted Answer

Use the `ddg-ai-chat` tool with the `keywords` argument to send a message or question to the AI. You can also specify the AI model to use with the `model` argument.

Question 14

How do I use the `search-results-summary` prompt?

Accepted Answer

Use the `search-results-summary` prompt with the `query` argument to specify the search term. You can also use the `style` argument to control the detail level (brief/detailed).

Question 15

How do I configure the server to work with Claude?

Accepted Answer

You need to modify the `claude_desktop_config.json` file in the appropriate directory (MacOS: `~/Library/Application Support/Claude/`, Windows: `%APPDATA%/Claude/`).  Detailed configuration examples for both development and published servers are provided in the documentation.

Question 16

How do I debug the MCP server?

Accepted Answer

Debugging MCP servers can be challenging. It's strongly recommended to use the [MCP Inspector](https://github.com/modelcontextprotocol/inspector) for the best debugging experience.

Question 17

Where can I find more information about UBOS and its AI Agent Development Platform?

Accepted Answer

Visit the UBOS website at [https://ubos.tech](https://ubos.tech) to learn more about their full-stack AI Agent Development Platform and how it can help you orchestrate AI Agents, connect them with your enterprise data, and build custom AI Agents.

DuckDuckGo Search API

Resources

Project Details

Recomended MCP Servers

Featured Templates

AI Video Generator

AI Chatbot Starter Kit

Python Bug Fixer

Service ERP

AI Chatbot Starter Kit v0.1

Talk with Claude 3

Start your free trial