ddgs-mcp
Provides web, news, image, and video search using Brave as one of the available metasearch backends, with support for region and time filters.
Provides web, news, image, and video search using DuckDuckGo as one of the available metasearch backends, with support for region and time filters.
Provides web, news, image, and video search using Google as one of the available metasearch backends, with support for region and time filters.
Provides web search using Mojeek as one of the available metasearch backends, with support for region and time filters.
Provides web search using Startpage as one of the available metasearch backends, with support for region and time filters.
Includes Wikipedia as one of the available sources in the metasearch backend pool, contributing results to the aggregated search responses.
Click on "Deploy 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., "@ddgs-mcp search the web for sustainable packaging innovations"
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.
ddgs-mcp
A Model Context Protocol (MCP) server that exposes DDGS (Dux Distributed Global Search) — a keyless, multi-engine web metasearch — to AI agents.
It is a drop-in, more reliable alternative to a single SearXNG instance: instead of one upstream that gets IP-banned and poisons every query, DDGS fans each call out over several backends (DuckDuckGo, Bing, Brave, Google, Mojeek, Startpage, Yahoo, Wikipedia, ...) and deduplicates the union. If one engine rate-limits you, the others still answer.
No API key. No account. Runs over stdio via uvx, matching the other MCP servers in this stack.
Install / run
uvx ddgs-mcp # from PyPI (once published)
uvx --from git+https://github.com/marcinkuk/ddgs-mcp.git ddgs-mcp # direct from gitFor local development:
cd ddgs-mcp
uv sync
uv run ddgs-mcpRelated MCP server: Alka Search MCP
Tools
Tool | Purpose |
| General web results (title, url, snippet). |
| News results with source + date. |
| Image results with direct image/thumbnail URLs. |
| Video results with embed URL, duration, publisher. |
| Read full readable content (markdown) of 1-5 URLs. |
| Diagnostics: version, configured backend/region, per-category backends, live ping. |
Each search tool accepts backend="auto" (randomized multi-engine, the default and most resilient) or a specific backend name, plus region, timelimit (d/w/m/y) and max_results.
All tools return a uniform envelope {"ok": bool, "engine": str, "count": int, "results": [...]}; on failure ok=false with a hint telling the agent how to retry (e.g. switch to auto or a different region).
Configuration (environment)
Variable | Default | Meaning |
|
| Default backend for search calls. |
|
| Default region code ( |
|
| Per-request timeout (seconds). |
| (unset) | Proxy URL passed to DDGS (e.g. |
|
| Server log verbosity. |
Agent Canvas registration
Register with a stdio MCP entry (no secrets required):
{
"ddgs": {
"transport": "stdio",
"command": "uvx",
"args": ["--from", "git+https://github.com/marcinkuk/ddgs-mcp.git", "ddgs-mcp"],
"enabled": true,
"description": "Keyless DDGS metasearch (DuckDuckGo/Bing/Brave/Google) + page extraction. Resilient SearXNG alternative."
}
}If you want ban-resistance, add an env entry for a rotating proxy:
"env": {"DDGS_PROXY": "http://127.0.0.1:1080"}The value is stored through the normal MCP config path (Fernet-encrypted at rest like the other secrets) — never commit it to this repo.
Why this over SearXNG?
Resilience: multi-backend aggregation survives single-engine bans (your exact
banuję mniesymptom).No key / no server: nothing to host;
uvxself-heals on container/image upgrades liketrailsearch-mcp.Extraction:
web_extractgives clean markdown of a page in one call.
Keep searxng registered alongside it if you like; the two can coexist and you can pick per query.
License
MIT.
Available Tools
6 toolsimage_searchA
Image search via DDGS (DuckDuckGo/Bing image backends). No API key.
Args: query: image query. max_results: number of results (1-25). region: e.g. "us-en", "wt-wt". safesearch: "on" | "moderate" | "off". backend: "auto" or one of: duckduckgo, bing.
Inputs: query (required), region, backend, safesearch, +1 more. Returns: object
news_searchA
News search via DDGS (DuckDuckGo/Bing/Yahoo news backends). No API key.
Args: query: news query. max_results: number of results (1-25). region: e.g. "us-en", "pl-pl", "wt-wt". timelimit: "d" | "w" | "m" | "y" or None. backend: "auto" or one of: duckduckgo, bing, yahoo. snippet_chars: max snippet length (0 = none).
Inputs: query (required), region, backend, timelimit, +2 more. Returns: object
search_statusA
Health/diagnostics: DDGS version, configured backend/region/timeout/proxy, available backends per category, and a live ping search.
Inputs: no named parameters. Returns: object
video_searchA
Video search via DDGS (DuckDuckGo video backend). No API key.
Args: query: video query. max_results: number of results (1-25). region: e.g. "us-en", "wt-wt". backend: "auto" or "duckduckgo". snippet_chars: max description length (0 = none).
Inputs: query (required), region, backend, max_results, +1 more. Returns: object
web_extractA
Extract readable content from 1-5 web pages (markdown by default).
Use after web_search/news_search to read the actual page content.
Args: urls: 1-5 absolute http(s) URLs to extract. max_chars: max characters of content returned per page (default 6000). fmt: "text_markdown" | "text_plain" | "text_rich" | "text" (raw HTML) | "content" (bytes->str).
Inputs: urls (required), fmt, max_chars. Returns: object
web_searchA
Web search (web results) via DDGS metasearch. No API key.
Args: query: search query. max_results: number of results (1-25). region: e.g. "us-en", "pl-pl", "de-de", "wt-wt" (worldwide, no region). safesearch: "on" | "moderate" | "off". timelimit: "d" (day), "w" (week), "m" (month), "y" (year), or None. backend: "auto" (randomized multi-engine, recommended) or specific: duckduckgo, bing, brave, google, mojeek, startpage, yahoo, wikipedia, grokipedia. snippet_chars: max snippet length per result (0 = no snippet).
Inputs: query (required), region, backend, timelimit, +3 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct content type or function: web, image, news, video, page extraction, and service diagnostics. There is no meaningful overlap in purpose, so an agent should rarely misselect among them.
Names are uniformly lowercase snake_case and mostly follow a `<type>_search` pattern for the four search tools. `web_extract` and `search_status` are minor structural deviations, but they remain clear and predictable in style.
Six tools is a well-scoped size for a search-focused server: four content-type searches, one extraction tool, and one diagnostics tool. Every tool has a clear role and none feel redundant or unnecessary.
The server covers the core search lifecycle: querying web, image, news, and video results, then extracting readable content from results, plus health diagnostics. There are no obvious missing operations for its stated purpose.
Related MCP Connectors
Free web search for AI agents. No API key required. Hosted MCP in active development.
Web search API and MCP server for developers building AI agents.
Scrape, crawl and search the web for AI agents via MCP.
Your agent needs the open web — searched by more than one engine, and read as clean markdown rather than raw HTML. **What you can ask for** • "Search this question with two providers and tell me where they disagree." • "Scrape these 40 URLs into markdown, in one batch." • "Crawl this documentation site and give me every page." • "Do deep research on this topic and cite the sources." • "Find the academic papers behind this claim." **How to use it** Point any MCP client at https://mcp.aisa.one/search/mcp and sign in with OAuth — there is no key to create or paste. 30 tools across several independent providers: Tavily and Exa search, answers, contents and agent runs; Firecrawl scrape, batch scrape, crawl, map and search; Perplexity Sonar, Sonar Pro, reasoning and deep research; Oxylabs AI search and LLM jobs; OpenAI and Anthropic web search; and scholarly search. **Why this rather than the source** Several independent indexes behind one account, because one engine's blind spot is not visible from inside it. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Find the page here, then ask the same agent who links to it or how much traffic it gets — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo-serp/mcp for the Google results page itself, https://mcp.aisa.one/seo-serp-other-engines/mcp for Bing, Baidu and Naver.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to perform multi-engine web search, fetch web pages, and extract clean Markdown content via MCP, with no API keys required.3252 PyPI11MIT
- AlicenseAqualityCmaintenanceFree web search, web-page reading as Markdown, and llms.txt documentation retrieval for MCP clients. Runs locally with Node.js over stdio using @alkasima/alka-search-mcp. Searches DuckDuckGo, Mojeek, and Brave; default providers require no API key. Website and provider availability may vary.351 npmMIT
- AlicenseAqualityCmaintenanceEnables any MCP client to run keyless multi-engine web searches with RRF fusion, fetch pages and documents as Markdown, and full-text search a local SQLite index. It keeps queries and cached content on the user's machine, degrading gracefully across engine tiers when providers are blocked or rate-limited.8MIT
- AlicenseNot gradedqualityCmaintenanceExposes metasearch across many engines and a page-to-Markdown fetcher as two MCP tools, web_search and web_fetch, so any MCP client can run searches and pull clean article content on demand. It also supports news-focused queries with category and time-range filters, plus optional inline page content.AGPL 3.0