A
licenseA
qualityA
maintenanceA Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
2
1,444
MIT
DuckDuckGo MCP Server
by zhsama
The DuckDuckGo MCP Server enables web searches with configurable parameters:
Execute web searches using the DuckDuckGo service for general queries, news, articles, and online content
Filter results by specifying the number of results (1-20) and applying SafeSearch levels (strict, moderate, or off)
Obtain results formatted in Markdown
Rate limits: 1 request per second and 15,000 requests per month
Allows performing web searches using the DuckDuckGo API, with support for configuring the number of results and SafeSearch settings
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., "@DuckDuckGo MCP Serversearch for latest AI developments in healthcare"
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.
duckduckgo-search MCP Server
English | 中文
A Model Context Protocol server for DuckDuckGo Search
This is a TypeScript-based MCP server that provides DuckDuckGo search functionality. It demonstrates core MCP concepts through:
Integration with DuckDuckGo Search
Easy-to-use search tool interface
Rate limiting and error handling support
Features
Search Tool
duckduckgo_search- Perform web searches using DuckDuckGo APIRequired parameter:
query(search query, max 400 characters)Optional parameter:
count(number of results, 1-20, default 10)Optional parameter:
safeSearch(safety level: strict/moderate/off, default moderate)Returns formatted Markdown search results
Rate Limits
Maximum 1 request per second
Maximum 15000 requests per month
Related MCP server: DuckDuckGo MCP Server
Development
Prerequisites
Node.js >= 18
pnpm >= 8.0.0
Installation
# Install pnpm if not already installed
npm install -g pnpm
# Install project dependencies
pnpm installBuild and Run
Build the server:
pnpm run buildFor development with auto-rebuild:
pnpm run watchSetup in Claude Desktop
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
# online
{
"mcpServers": {
"duckduckgo-search": {
"command": "npx",
"args": [
"-y",
"duckduckgo-mcp-server"
]
}
}
}
# local
{
"mcpServers": {
"duckduckgo-search": {
"command": "node",
"args": [
"/path/to/duckduckgo-search/build/index.js"
]
}
}
}
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
pnpm run inspectorThe Inspector will provide a URL to access debugging tools in your browser.
Available Tools
1 toolduckduckgo_web_searchB
Performs a web search using the DuckDuckGo, ideal for general queries, news, articles, and online content. Use this for broad information gathering, recent events, or when you need diverse web sources. Supports content filtering and region-specific searches. Maximum 20 results per request.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of results (1-20, default 10) | |
| query | Yes | Search query (max 400 chars) | |
| safeSearch | No | SafeSearch level (strict, moderate, off) | moderate |
TDQS
B3.4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context like 'maximum 20 results per request' and mentions content filtering and region-specific searches, but does not cover aspects like rate limits, authentication needs, or error handling, leaving gaps in behavioral understanding.
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 sized with three sentences that efficiently cover purpose, usage, and constraints. It is front-loaded with the core function and avoids unnecessary repetition, though minor improvements in flow could elevate it to a 5.
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 moderate complexity (3 parameters, no output schema, no annotations), the description provides a basic overview but lacks details on return values, error cases, or advanced usage. It is adequate for a simple search tool but incomplete for robust agent interaction.
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 description coverage is 100%, so the schema fully documents all parameters. The description does not add any parameter-specific details beyond what the schema provides, such as explaining the impact of 'safeSearch' levels or query formatting. Baseline 3 is appropriate as the schema handles the heavy lifting.
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 'performs a web search using DuckDuckGo' with specific use cases like 'general queries, news, articles, and online content.' It distinguishes itself as a general-purpose search tool, though without sibling tools to differentiate from, it cannot achieve a perfect 5.
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 provides implied usage guidance with phrases like 'ideal for general queries' and 'use this for broad information gathering,' but lacks explicit when-not-to-use scenarios or alternatives. Without sibling tools, it cannot offer comparative guidance, limiting its score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
B3.4/5.0
Disambiguation5/5
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as performing web searches using DuckDuckGo.
Naming Consistency5/5
Since there is only one tool, naming consistency is inherently perfect. The tool name 'duckduckgo_web_search' follows a clear verb_noun pattern that would be appropriate if more tools were added.
Tool Count2/5
A single tool for a web search server is too minimal for the apparent scope. While the tool covers basic search functionality, a more complete surface would likely include additional tools such as for image search, news search, or advanced query options, making this feel thin and incomplete.
Completeness2/5
The tool surface is severely incomplete for a DuckDuckGo server. It only provides general web search, missing obvious functionalities like image search, video search, instant answers, or autocomplete, which are core features of DuckDuckGo. This will limit agents to basic queries without specialized capabilities.
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
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
MCP server for Google search results via SERP API
Related MCP Servers
- FlicenseBqualityDmaintenanceA server that provides DuckDuckGo search capabilities (text, image, news, video search and AI chat) through the Model Context Protocol.516
- AlicenseCqualityDmaintenanceA Model Context Protocol server implementation that enables AI assistants like Claude to perform Google searches and retrieve web data directly through natural language requests.1389168MIT
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables AI applications like Claude Desktop and Cursor IDE to perform web searches via DuckDuckGo's search engine.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/zhsama/duckduckgo-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server