ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 4/5

searxng-search

Web search using SearXNG instance via MCP. Provides web search capability for agents with configurable SearXNG endpoint.

Why use this skill?

Integrate SearXNG web search into your OpenClaw agent. Get unbiased search results in JSON, Markdown, or text. Essential for research and information gathering.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/zfanmy/searxng-search-2
Or

What This Skill Does

The SearXNG Search skill provides your OpenClaw agent with powerful web searching capabilities by integrating with a SearXNG instance. SearXNG is a free and open-source metasearch engine that aggregates results from various search engines without tracking users. This skill allows agents to perform web searches, retrieve results in different formats (JSON, Markdown, plain text), and customize the search query with parameters like the number of results. It acts as a bridge between the agent's natural language queries and the SearXNG API, enabling informed decision-making and information retrieval.

Installation

To install the SearXNG Search skill, you will need to have mcporter and Python 3.8+ installed. First, copy the config.json file provided with the skill to your mcporter configuration directory, typically located at ~/.config/mcporter/config.json. Ensure you have mcporter installed globally by running npm install -g mcporter.

Next, you need to configure your SearXNG instance. This can be done by setting the SEARXNG_URL environment variable to the address of your SearXNG instance (e.g., export SEARXNG_URL="http://your-searxng-instance:port"). Alternatively, you can configure this within your mcporter setup by modifying its config.json to include the searxng server details with the appropriate environment variable.

Finally, install the skill using the OpenClaw command: clawhub install openclaw/skills/skills/zfanmy/searxng-search-2.

Use Cases

This skill is ideal for agents that require up-to-date information from the web. It can be used for research tasks, fact-checking, summarizing current events, finding specific online resources, or gathering competitive intelligence. For example, an agent could use this skill to research the latest advancements in a particular technology, find reviews for a product, or compare pricing across different online retailers. It enhances the agent's ability to act autonomously by providing it with direct access to a vast amount of information without relying on pre-programmed knowledge.

Example Prompts

  1. "Search the web for recent developments in AI ethics and summarize the top 3 findings."
  2. "Find the official documentation for the 'numpy' Python library and provide the link."
  3. "What are the main features of the latest iPhone model, and present them in a bulleted list?"

Tips & Limitations

Ensure your SearXNG instance is accessible and correctly configured. For optimal results, experiment with different search queries to refine the information gathered. Be aware that the quality of search results depends heavily on the SearXNG instance's configuration and the search engines it aggregates from. The skill relies on mcporter and its dependencies; ensure they are up-to-date. The curl and jq utilities are required for the bash script usage. The output format can be toggled between text, json, and markdown for flexibility in how the agent processes the information.

Metadata

Author@zfanmy
Stars879
Views16
Updated2026-02-11
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-zfanmy-searxng-search-2": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#search#web#information retrieval#metasearch
Safety Score: 4/5

Flags: network-access, external-api