Access to Brave search results through SearXNG's aggregated search functionality
Access to DuckDuckGo search results through SearXNG's aggregated search functionality
Access to Google search results through SearXNG's aggregated search functionality
Provides privacy-focused web search capabilities through SearXNG metasearch engine, enabling web, image, video, and news searches across multiple search engines without tracking
Access to Wikipedia search results through SearXNG's aggregated search functionality
Access to YouTube video search results through SearXNG's aggregated search functionality
š SearXNG MCP Server
A privacy-focused Model Context Protocol (MCP) server that provides Claude with web search capabilities through SearXNG metasearch engine.
⨠Features
š Privacy-first - No tracking, no data collection via SearXNG
š Multi-engine - Aggregates results from Google, Bing, DuckDuckGo, Brave, and more
šÆ Specialized search - Web, images, videos, and news search
ā” Fast - Optimized with minimal tool set (4 tools)
š³ Docker included - SearXNG instance setup included
š ļø Easy setup - Python-based with UV package manager
š¦ Installation
Prerequisites
Python 3.10 or higher
Docker and Docker Compose
Git
Quick Install
1. Clone repository:
2. Configure SearXNG:
Edit the following files with your settings:
docker-compose.yml
- ReplaceYOUR_IP
with your server's IP addressdocker-compose.yml
- ReplaceCHANGE_THIS_SECRET_KEY
with a secret keysearxng/settings.yml
- ReplaceCHANGE_THIS_TO_YOUR_OWN_SECRET_KEY
with the same secret keysearxng-config/config.json
- ReplaceYOUR_IP
with your server's IP address
Generate a secret key:
3. Start SearXNG instance:
SearXNG will be available at http://YOUR_IP:8080
4. Install MCP server (using UV - recommended):
5. Verify installation:
āļø Configuration
MCP Client Setup
Add to your MCP settings (e.g., Claude Desktop config):
SearXNG Configuration
The SearXNG instance is configured via searxng/settings.yml
:
Default engines: Google, Bing, DuckDuckGo, Brave, Wikipedia, YouTube
JSON API enabled for MCP access
Privacy features enabled (no tracking)
Accessible on your LAN at YOUR_IP:8080
IMPORTANT: Before starting Docker, replace the following in your config files:
docker-compose.yml
: ReplaceYOUR_IP
andCHANGE_THIS_SECRET_KEY
searxng/settings.yml
: ReplaceCHANGE_THIS_TO_YOUR_OWN_SECRET_KEY
searxng-config/config.json
: ReplaceYOUR_IP
Generate secret key: openssl rand -hex 32
MCP Server Configuration
Edit searxng-config/config.json
(replace YOUR_IP with your server's IP):
š§ Available Tools
The server provides 3 optimized tools designed for efficient research:
1. search - Quick Web/News Search
Quick single search for web or news content.
Use when:
Need quick information or simple lookup
User asks for a basic web search
Looking for news on a topic
Parameters:
query*
- What to search forcategory
- "general" (default) or "news"engines
- Optional: Specific engines (e.g., "google,bing")max_results
- Number of results (default: 10, max: 50)
Example:
2. search_media - Images & Videos
Search for images or videos.
Use when:
User wants to find images or photos
Looking for video content
"show me pictures of..." or "find videos about..."
Parameters:
query*
- What to findmedia_type
- "images" (default) or "videos"engines
- Optional: Specific enginesmax_results
- Number of results (default: 10, max: 50)
Example:
3. research_topic - Deep Research ā
Multi-search research with automatic analysis and synthesis.
Use when:
User wants comprehensive research or briefing
Need to validate information across multiple sources
User asks to "research", "investigate", or "analyze"
Creating detailed reports with cross-referenced sources
What it does:
Runs 2-6 searches automatically using different strategies
Searches multiple engines (Google, Bing, DuckDuckGo, Brave, Wikipedia)
Combines general web + news sources
Deduplicates results across all searches
Returns 15-50 UNIQUE sources
Instructs Claude to analyze and synthesize (not just list sources)
Critical behavior: After gathering sources, Claude is instructed to:
Read and analyze ALL sources
Cross-reference claims across sources
Identify high-confidence facts (confirmed by many sources)
Note contradictions or single-source claims
Create comprehensive briefing with executive summary
Assess source quality and credibility
Parameters:
query*
- Research topic or questiondepth
- Research thoroughness:"quick"
- 2 searches, ~15 unique sources"standard"
- 4 searches, ~30 unique sources (recommended)"deep"
- 6 searches, ~50 unique sources
Example:
š” Usage Examples
General search:
Image search:
Video search:
News search:
š³ Docker Management
Start SearXNG:
Stop SearXNG:
View logs:
Rebuild:
š ļø Development
Run tests:
Format code:
Type checking:
Lint:
šÆ Why Only 4 Tools?
This MCP server is optimized for efficiency:
Focused functionality - Each tool has a clear, distinct purpose
LLM-friendly - Tool descriptions include "Use this when..." guidance
Low context - Minimal tool set reduces token usage
Privacy-first - SearXNG aggregates without tracking
Unlike direct search engine APIs, SearXNG provides:
Privacy protection (no tracking)
Multi-engine aggregation
Self-hosted control
No API keys needed
š Project Structure
š License
MIT License
š Credits
SearXNG - Privacy-respecting metasearch engine
Model Context Protocol - MCP specification
Built with FastMCP
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Provides privacy-focused web search capabilities through SearXNG metasearch engine, enabling web, image, video, and news searches without tracking. Includes comprehensive research tools that aggregate and analyze results from multiple search engines.