# nickclyde/duckduckgo-mcp-server

A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.

Repository: https://github.com/nickclyde/duckduckgo-mcp-server
Canonical: https://ross.abutalabs.com/products/duckduckgo-mcp-server
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-28T14:23:09+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 95, longevity 39
- inputs: {"age_days": 557, "days_push": 36, "days_rel": 36, "gap_med": 18.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1439, forks 186 (observed 2026-08-28T04:04:44.079462+00:00)

## What it is
A Model Context Protocol (MCP) server that exposes DuckDuckGo web search to LLM clients like Claude Desktop and Claude Code. It also fetches and parses webpage content, with rate limiting and LLM-friendly output formatting.

## Use cases
- give claude the ability to search the web via duckduckgo
- add web search to an mcp-compatible ai assistant
- let an llm fetch and parse webpage content
- free web search tool for ai agents without api keys
- configure safe search and region for llm web searches

## When to choose
- you use Claude Desktop, Claude Code, or another MCP client and need web search
- you want a keyless, free search backend for LLM agents
- you need SafeSearch and region configuration for search results

## When to avoid
- you need search results outside an MCP/LLM context
- you require a search API with guaranteed SLA or high-volume scraping
- you need results from a specific engine like Google or Bing

## Facets
- artifact type: service
- maturity: active
- function: search-engine, web-scraping, mcp, parser, http-client
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: duckduckgo, mcp-server, web-search, claude-desktop, llm-tools, search

## Member repositories
- nickclyde/duckduckgo-mcp-server (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.079462+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:36:37.050386+00:00, confidence not recorded.
  - readme: https://github.com/nickclyde/duckduckgo-mcp-server (fetched 2026-08-28T04:04:44.079462+00:00, sha a62b2a22a115)
  - registry_pypi: https://pypi.org/pypi/duckduckgo-mcp-server/json (fetched 2026-08-29T11:47:02.337343+00:00, sha 28aa79d910bf)
- Data as of 2026-08-30T08:39:29.467469+00:00.