Skip to main content
Glama
enesjakozh
gianlucamazza

MCP DuckDuckGo Search Plugin

by gianlucamazza
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

MCP DuckDuckGo

A Model Context Protocol (MCP) server that provides web search capabilities using DuckDuckGo. This server enables LLMs to search the web and retrieve detailed content from websites through structured data extraction.

Key Features

  • Fast and reliable. Uses DuckDuckGo's web interface with robust HTML parsing

  • LLM-friendly. Returns structured data optimized for AI consumption

  • Content extraction. Intelligently extracts and summarizes webpage content

  • Related searches. Generates contextual search suggestions

Related MCP server: MCP DuckDuckGo

Requirements

  • Python 3.10 or newer

  • VS Code, Cursor, Windsurf, Claude Desktop, Goose or any other MCP client

Getting started

First, install the DuckDuckGo MCP server with your client.

Standard config works in most of the tools:

{
  "mcpServers": {
    "duckduckgo-search": {
      "command": "mcp-duckduckgo"
    }
  }
}

Claude Code

Use the Claude Code CLI to add the DuckDuckGo MCP server:

claude mcp add duckduckgo-search mcp-duckduckgo

For global configuration (available in all projects):

claude mcp add duckduckgo-search --scope user mcp-duckduckgo

Claude Desktop

Follow the MCP install guide, use the standard config above.

Cursor

Go to Cursor Settings -> MCP .

Click the button to install:

Install in Cursor

Or install manually:

Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, use command type with the command mcp-duckduckgo.

VS Code

Click the button to install:

Install in VS Code

Or install manually:

Follow the MCP install guide, use the standard config above.

You can also install the DuckDuckGo MCP server using the VS Code CLI:

code --add-mcp '{"name":"duckduckgo-search","command":"mcp-duckduckgo"}'

After installation, the DuckDuckGo MCP server will be available for use with your GitHub Copilot agent in VS Code.

Windsurf

Follow Windsurf MCP documentation. Use the standard config above.

Goose

Click the button to install:

Install in Goose

Or install manually:

Go to Advanced settings -> Extensions -> Add custom extension. Name to your liking, use type STDIO, and set the command to mcp-duckduckgo. Click "Add Extension".

LM Studio

Click the button to install:

Add MCP Server duckduckgo to LM Studio

Or install manually:

Go to Program in the right sidebar -> Install -> Edit mcp.json. Use the standard config above.

Configuration

DuckDuckGo MCP server supports following arguments:

mcp-duckduckgo --help

Available options:

--port PORT        Port number for the MCP server (default: 3000)
--version          Show program's version number and exit
--help             Show help message and exit

Environment Variables

  • MCP_PORT: Set the port number for the server (default: 3000)

Example usage:

# Set port via environment variable
export MCP_PORT=8080
mcp-duckduckgo

# Or set it inline
MCP_PORT=8080 mcp-duckduckgo

Available Tools

web_search

  • Title: Web Search

  • Description: Search the web using DuckDuckGo

  • Parameters:

    • query (string): Search query (max 400 characters)

    • max_results (number, optional): Maximum number of results to return (1-20, default 10)

  • Read-only: false

get_page_content

  • Title: Get Page Content

  • Description: Retrieve and extract content from a web page

  • Parameters:

    • url (string): URL to fetch content from

  • Read-only: false

suggest_related_searches

  • Title: Suggest Related Searches

  • Description: Generate contextual search suggestions based on a query

  • Parameters:

    • query (string): Original search query

    • max_suggestions (number, optional): Maximum suggestions to return (1-10, default 5)

  • Read-only: true

Installation from Source

If you need to install from source or development:

Using uv (Recommended)

uv is a fast Python package manager:

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install from GitHub
uv tool install git+https://github.com/gianlucamazza/mcp-duckduckgo.git

Using pip

# Clone and install
git clone https://github.com/gianlucamazza/mcp-duckduckgo.git
cd mcp-duckduckgo
pip install -e .

Development Installation

git clone https://github.com/gianlucamazza/mcp-duckduckgo.git
cd mcp-duckduckgo

# Install in development mode
pip install -e .

# Run tests
pip install -e ".[test]"
pytest

License

MIT

Repository

GitHub Repository

Available Tools

3 tools
get_page_contentC

Fetch and extract content from a web page.

Returns the page title, description, and main content.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL to fetch content from

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions what the tool returns ('page title, description, and main content'), which is helpful, but lacks critical details like error handling, rate limits, authentication needs, or performance characteristics. For a web-fetching tool, this leaves significant gaps in understanding its behavior.

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

Conciseness4/5

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

The description is appropriately concise with two sentences that directly address purpose and return values. It's front-loaded with the core functionality. However, the second sentence could be more integrated with the first for better flow, and there's some whitespace formatting that slightly affects structure.

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 has an output schema (which handles return value documentation) and 100% schema coverage for the single parameter, the description provides adequate context for basic understanding. However, for a web content extraction tool with no annotations, it should ideally mention common constraints like URL validation, content type limitations, or network timeout behavior to be more complete.

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?

The input schema has 100% description coverage, with the 'url' parameter clearly documented. The description adds no additional parameter semantics beyond what's in the schema. According to scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no param info in the description.

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

Purpose4/5

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

The description clearly states the tool's purpose with specific verbs ('fetch and extract content from a web page') and identifies the resource ('web page'). It distinguishes from sibling tools like 'suggest_related_searches' and 'web_search' by focusing on content extraction rather than search or suggestions. However, it doesn't explicitly differentiate itself from potential similar tools not in the sibling list.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'web_search' or 'suggest_related_searches'. There's no mention of prerequisites, constraints, or typical use cases. The agent must infer usage from the purpose alone, which is insufficient for optimal tool selection.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: get_page_content extracts content from a specific URL, web_search performs general web searches, and suggest_related_searches provides autocomplete suggestions. There is no overlap in functionality, making tool selection straightforward for an agent.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_page_content, suggest_related_searches, web_search) using snake_case. The naming is predictable and readable, with no deviations in style or convention.

Tool Count5/5

With 3 tools, the server is well-scoped for a DuckDuckGo search plugin. Each tool serves a distinct and essential function in the search workflow, from performing searches to extracting content and getting suggestions, with no unnecessary redundancy.

Completeness4/5

The tool surface covers core search operations effectively, including searching, content extraction, and related suggestions. A minor gap exists in advanced search features like filtering by date or region, but agents can work around this with the provided tools for most use cases.

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

Appeared in Searches

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/gianlucamazza/mcp-duckduckgo'

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