SearXNG MCP Server
Enables web search through SearXNG instances, offering tools for general and category-specific queries, engine selection, time filtering, and engine discovery.
README
SearXNG MCP Server
A Model Context Protocol (MCP) server that provides web search capabilities through SearXNG instances.
Features
- 🔍 Web Search — Query any SearXNG instance for general web results
- 📁 Category-Specific Search — Search images, videos, news, music, science, etc.
- ⚙️ Engine Selection — Use specific search engines (Google, Bing, DuckDuckGo, etc.)
- 🕐 Time Filtering — Filter results by day, week, month, or year
- 📋 Engine Discovery — List all available SearXNG engines
Installation
From PyPI (when published)
pip install searxng-mcp-server
From Source
git clone https://github.com/<username>/searxng-mcp-server.git
cd searxng-mcp-server
pip install -e ".[dev]"
Configuration
Set the following environment variables:
| Variable | Description | Default |
|---|---|---|
SEARXNG_URL |
SearXNG instance URL | http://localhost:8888 (local Docker) |
SEARXNG_ENGINES |
Comma-separated engine list | (none — uses all) |
SEARXNG_LANG |
Search language code | en-US |
Example:
export SEARXNG_URL="http://localhost:8888"
export SEARXNG_ENGINES="google,bing,duckduckgo"
export SEARXNG_LANG="zh-TW"
Usage with Hermes Agent
Add to ~/.hermes/config.yaml:
mcp_servers:
searxng:
command: "uv"
args: ["run", "--directory", "/path/to/searxng-mcp-server", "searxng-mcp"]
env:
SEARXNG_URL: "https://search.sapti.me"
Usage with Claude Desktop / Cursor / VS Code
Add to your MCP configuration:
{
"mcpServers": {
"searxng": {
"command": "uv",
"args": ["run", "--directory", "/path/to/searxng-mcp-server", "searxng-mcp"],
"env": {
"SEARXNG_URL": "https://search.sapti.me"
}
}
}
}
Available Tools
search_web
Search the web using a SearXNG instance.
Parameters:
query(string, required): The search querymax_results(int, optional): Maximum results to return (default: 10)time_range(string, optional): Filter by time — 'day', 'week', 'month', 'year'
search_specific
Search using specific categories and/or engines.
Parameters:
query(string, required): The search querycategories(list of strings, optional): Categories to search (general, images, videos, news, music, files, it, science, social media)engines(list of strings, optional): Specific engines to usemax_results(int, optional): Maximum results (default: 10)time_range(string, optional): Time filter
search_by_category
Search a specific SearXNG category.
Parameters:
query(string, required): The search querycategory(string, optional): Category to search (default: 'general')max_results(int, optional): Maximum results (default: 10)
list_engines
List all available SearXNG search engines from searxng.org.
Parameters: None
Development
# Install dependencies
pip install -e ".[dev]"
# Run tests
pytest tests/
# Lint with ruff
ruff check src/ tests/
Public SearXNG Instances
You can use any public or self-hosted SearXNG instance. Some public instances:
https://search.sapti.mehttps://searx.behttps://search.ononoki.org
⚠️ Note: Public instances may have rate limits or be unreliable. For production use, consider self-hosting your own SearXNG instance.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.