Skip to main content
Glama
zopalz

DuckDuckGo MCP Server

by zopalz
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

DuckDuckGo MCP Server

A simple Model Context Protocol (MCP) server that provides web search, image search, and image download capabilities using the duckduckgo_search library.

Features

  • Web Search: Search the web using DuckDuckGo with customizable region and result limits

  • Image Search: Search for images with filters for size and type

  • Image Download: Download images from URLs to your local machine

Related MCP server: EZ Web Search MCP Server

Installation

Using uv (Recommended)

  1. Install uv if you haven't already:

curl -LsSf https://astral.sh/uv/install.sh | sh

  1. Clone this repository or download the files

  2. Create a virtual environment and install dependencies:

uv venv
uv pip install -r requirements.txt

Using pip

  1. Clone this repository or download the files

  2. Install dependencies:

pip install -r requirements.txt

Usage

Running the Server

With uv (from the project directory):

uv run python server.py

Or activate the virtual environment first:

source .venv/bin/activate  # On Windows: .venv\Scripts\activate
python server.py

With standard Python:

python server.py

Configuring in Claude Desktop

Add this configuration to your Claude Desktop config file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

Using uv (recommended):

{
  "mcpServers": {
    "duckduckgo-search": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/websearch_mcp",
        "run",
        "python",
        "server.py"
      ]
    }
  }
}

Using Python directly with virtual environment:

{
  "mcpServers": {
    "duckduckgo-search": {
      "command": "/absolute/path/to/websearch_mcp/.venv/bin/python",
      "args": ["/absolute/path/to/websearch_mcp/server.py"]
    }
  }
}

Available Tools

web_search

Search the web using DuckDuckGo.

Parameters:

  • query (required): The search query

  • max_results (optional): Maximum number of results (default: 10)

  • region (optional): Region code (default: "wt-wt" for worldwide)

    • Examples: "us-en", "uk-en", "de-de", "fr-fr"

Example:

Search the web for "Python MCP servers" with max 5 results

image_search

Search for images using DuckDuckGo.

Parameters:

  • query (required): The image search query

  • max_results (optional): Maximum number of results (default: 10)

  • size (optional): Image size filter

    • Options: "small", "medium", "large", "wallpaper"

  • type (optional): Image type filter

    • Options: "photo", "clipart", "gif", "transparent", "line"

Example:

Search for "cute puppies" images, large size, photo type, max 5 results

download_image

Download an image from a URL to your local machine.

Parameters:

  • url (required): The URL of the image to download

  • filename (optional): Custom filename for the downloaded image

  • download_dir (optional): Directory to save the image (default: "./downloads")

Example:

Download image from https://example.com/image.jpg to ./my-images/

Dependencies

License

See LICENSE file for details.

Notes

  • Images are downloaded to ./downloads by default

  • The download directory will be created automatically if it doesn't exist

  • Web search respects DuckDuckGo's rate limits

  • All searches are anonymous (no tracking)

Available Tools

3 tools
download_imageA

Download an image from a URL to the local machine. Returns the local file path.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL of the image to download
filenameNoOptional filename for the downloaded image. If not provided, will use the original filename from the URL.
download_dirNoDirectory to save the image (default: ./downloads)./downloads

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions the return value (local file path) but does not disclose overwrite behavior, directory creation, authentication requirements, error handling for invalid URLs, or whether the operation is synchronous. These gaps are significant for a mutation-like tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with a secondary sentence about the return value. No wasted words; essential information is front-loaded. Highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (3 simple parameters, no nested objects, no output schema), the description covers the core purpose and return value. However, it omits important details like default behavior for filename conflicts, directory creation, error outcomes, and supported file formats. It is adequate but could be more thorough to avoid ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema documentation coverage is 100% (all parameters have descriptions). The tool description adds no further explanation beyond stating the overall purpose. Baseline 3 is appropriate since the schema already explains each parameter adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action ('Download'), the resource ('an image from a URL'), and the result ('Returns the local file path'). It effectively distinguishes from sibling tools (image_search, web_search) which are search-oriented, not download-oriented.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when needing to save an image locally from a given URL. However, it does not explicitly state when not to use it or mention alternatives. The context of siblings being distinct search tools provides indirect guidance, but explicit usage conditions are absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 3 tool updatesv0.1.0
    • First observeddownload_image
    • First observedimage_search
    • First observedweb_search
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

Each tool has a distinct purpose: web_search for web results, image_search for image results, and download_image for saving images locally. No overlap.

Naming Consistency5/5

All tools follow the same verb_noun snake_case pattern: download_image, image_search, web_search.

Tool Count5/5

Three tools are well-scoped for a search server covering web search, image search, and image downloading. Not too few or too many.

Completeness4/5

Core search and download functionality is covered. Minor gaps exist (e.g., no video or news search), but the surface is sufficient for basic DuckDuckGo tasks.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • EZ Web Search MCP Server

    Gnarus-G
    F
    license
    A
    quality
    D
    maintenance
    A simple MCP server that provides web search functionality via DuckDuckGo, returning titles, URLs, and descriptions for results. Configurable result limit.
    1
    -

  • scrapesearch-mcp

    tonmoy-dhroubo
    F
    license
    Not graded
    quality
    D
    maintenance
    MCP server that provides web search scraping from DuckDuckGo (with Mojeek fallback) and URL content fetching as markdown/text or raw HTML.
    1
    -

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zopalz/websearch_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server