SkillFoxx

DDGS MCP

A metasearch MCP server: the agent searches text, images, news, videos and books across many engines and extracts page content

  • 3,065 ★ on the repository
  • Last commit
  • MIT
MCP server

Extended access

Why this level

  • Goes to the network and queries third-party engines
  • Extracts content from arbitrary pages
All reasons and checks

deedy5/ddgsAuthor:deedy5

Install

Manual install

pip install -U ddgs[mcp]

Installs the package with the MCP server. The base ddgs and the API-server variant install separately.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Goes to the network and queries third-party engines
  • Extracts content from arbitrary pages

This is third-party code. Review the repository files before installing.

What it does

DDGS is a metasearch library that aggregates results from various web search services. Beyond a Python class and a CLI, it provides a FastAPI API server and an MCP server over stdio. The MCP server gives the agent the search_text, search_images, search_news, search_videos, search_books and extract_content tools for pulling content from a URL. Text search runs through engines such as bing, brave, duckduckgo, google, mojeek, startpage, yandex, yahoo, wikipedia and others, with proxy support. This gives the agent web search without keys for individual search APIs.

Who it is for. For developers and analysts who need multi-source web search for the agent without separate keys.

Good fit when

  • You want the agent to search the web across several engines at once
  • You need images, news, videos or books through one interface
  • You need to extract page content from a URL

Not a fit when

  • You need one specific engine with an official API and agreement
  • You cannot run a local search process

Example request

Find recent news on the topic across several engines and extract the text of the most relevant page

MCP

Transport
stdio
Authentication
not required

Limitations

DDGS aggregates results from different engines, so behavior depends on their availability and responses, and some engines may need a proxy. It is metasearch without official agreements with the search systems, so respect their terms. The MCP server installs as an extra package option.

How to disable. Remove the ddgs entry from the MCP client config and uninstall the ddgs package.

FAQ

Which tools does the MCP server provide?

search_text, search_images, search_news, search_videos, search_books and extract_content for pulling page content.

Do I need engine keys?

No. DDGS aggregates results from different engines without separate keys, but respect those services' terms.

Discussion

No questions or reviews yet.

MCP servers

Web search via DuckDuckGo and page reading for the agent with no API keys, with built-in rate limiting

MCP serverExtended access1.6K

Local web search for an agent with no API keys: results are ranked on your machine and only the relevant passages come back

MCP serverExtended access151

Metasearch for agents: one MCP server and HTTP API merge results from many search providers into unified JSON with deduplication.

MCP serverExtended access58
Russian stack

An MCP web-search and content-extraction server via Yandex and Google on top of SerpAPI, geared toward RU/CIS results

MCP serverExtended access1

MCP server with DuckDuckGo search and page text extraction: several URLs can be passed in one call

MCP serverExtended access151

README in short

The README describes DDGS as a metasearch library that aggregates results from many web engines. It installs via pip, with variants for a FastAPI API server and an MCP server over stdio. It offers text, image, video, news and book search plus content extraction from a URL, with engines including bing, brave, duckduckgo, google, yandex, startpage, mojeek and others. It shows the CLI, API startup, docker-compose and MCP config for Cursor and Claude Desktop, with proxy support. MIT licensed.

README badge

Report a problem