A local Model Context Protocol (MCP) server that provides fast, API-key-free web search capabilities across text, images, and news.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install websearch-ddgs-mcp
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install websearch-ddgs-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is DDGS Web Search?
The DDGS Web Search skill leverages a local DuckDuckGo Search (DDGS) MCP server to provide high-performance search capabilities to your AI agents. By utilizing an SSE-based architecture via mcporter, this Openclaw Skills integration allows for seamless retrieval of web content, including specialized searches for books, videos, and real-time news, all without the friction of managing external API keys or subscriptions.
Designed for speed and reliability, it operates as a bridge between the agent and the web. It is particularly effective for automated workflows or cron runs where consistent, programmatic access to search engine results pages (SERP) is required. With support for multiple backends like DuckDuckGo and Bing, it ensures high availability for your search-dependent tasks.
DDGS Web Search Use Cases
- Performing general web research and fact-checking during automated agent runs.
- Fetching the latest news updates with specific time-sensitive filters.
- Searching for and retrieving metadata for images, videos, and books.
- Executing search tasks in environments where external API access is restricted or cost-prohibitive.
How DDGS Web Search Works
- The DDGS Python package is installed and initialized as a local API server on a specific host and port.
- The server exposes an MCP-compliant SSE (Server-Sent Events) endpoint at a local URL.
- The mcporter tool connects to this local endpoint, registering the available search tools into the agent's environment.
- When a search query is triggered, the agent calls specific tools (e.g., ddgs.search_text) with parameters for region, backend, and result count.
- The local server fetches the data from the web and returns a structured JSON response to the agent for processing.
DDGS Web Search Setup
Prerequisites
Ensure python3 and mcporter are installed on your system.
Installation
First, install the required Python package:
python3 -m pip install -U ddgs
Start the MCP Server
Run the server in the background to make it available for Openclaw Skills:
ddgs api -d --host 127.0.0.1 --port 8000
Register with mcporter
Connect mcporter to the local DDGS service:
mcporter config add ddgs http://127.0.0.1:8000/sse --allow-http
DDGS Web Search Data Schema & Taxonomy
The skill returns data in a structured JSON format. Below are the primary fields available in search results:
| Field | Description |
|---|---|
query |
The original search string provided to the engine. |
max_results |
The maximum number of items returned (default is 10). |
backend |
The engine used (e.g., duckduckgo, bing, annasarchive). |
results |
An array of objects containing titles, URLs, and snippets. |
safesearch |
The filter level applied to the search results. |
DDGS Web Search Advanced Features
- Multi-backend support allowing fallback to Bing or Anna's Archive when primary engines are throttled.
- Background daemonization via systemd for persistent 'always-on' search capabilities.
- Specialized news filtering using the timelimit parameter (day, week, month, year).
- Local API documentation accessible at http://localhost:8000/docs for custom tool development.
- SSE (Server-Sent Events) integration for real-time communication within the Openclaw Skills ecosystem.
SKILL.md
Loading
Related Openclaw Skills
Store
A comprehensive retail operations framework for managing physical stores, inventory, and staff rhythm using local-first AI workflows.
Agent Reputation Tracker
Establish verifiable credibility and track prediction accuracy for AI agents on the SuperColony hive via the Demos blockchain.
Her
A sophisticated persona steering layer that transforms your AI assistant into an emotionally attuned, elegant companion through SOUL.md modification.
Betting
A professional-grade betting analysis framework that prioritizes price integrity, implied probability, and bankroll discipline over speculative narratives.
File Backup Skill
An automated safeguard that creates temporary backups of critical files before any modifications occur, ensuring data integrity for Openclaw Skills.
Markdown Fetcher
An intelligent tool that converts complex web content into clean, readable Markdown using a prioritized list of high-performance fetching services.
Featured*
