mcp-searxng-public-extended
Free web search for your AI using public SearXNG instances, with parallel multi-server requests and throttling.
README
mcp-searxng-public-extended
English | Chinese
Free web search for your AI using public SearXNG instances.
Acknowledgment: Inspired by pwilkin/mcp-searxng-public, extended with parallel multi-server requests, global throttling, configurable parameters, and bilingual schema support (zh/en).
Features
- HTML Parsing: Most public SearXNG instances disable JSON API, this server parses HTML responses directly
- Rich Parameters: categories, engines, safesearch, time range, language, pagination, return fields
- Parallel Racing & Deduplication: Randomly select
BATCH_SIZEservers, query in parallel, merge results from topMIN_SERVERSfastest - Auto Throttling: Per-server request queue with configurable minimum interval, preventing rate limiting from public instances
Usage with MCP Clients
Add to your MCP client configuration:
{
"mcpServers": {
"searxng": {
"args": [
"-y",
"@johnnren/mcp-searxng-public-extended"
],
"command": "npx",
"env": {
"SEARXNG_BASE_URL": "https://opnxng.com;https://priv.au",
"SEARXNG_DEFAULT_ENGINES": "google,duckduckgo,brave",
"SEARXNG_DEFAULT_PAGES": "1",
"SEARXNG_DEFAULT_SAFESARCH": "0",
"SEARXNG_RESULT_FIELDS": "url,title,summary",
"SEARXNG_VISIBLE_PARAMETERS": "query,categories,time_range,language,startPage"
}
}
}
}
Hiding
pagesandengineswithSEARXNG_VISIBLE_PARAMETERSimproves stability (not all servers support all engines) and reduces response size (one page is usually enough).
Environment Variables
| Variable | Description | Default |
|---|---|---|
SEARXNG_BASE_URL |
SearXNG server URLs (semicolon-separated) Required | - |
SEARXNG_SCHEMA_LANG |
Schema language: zh (Chinese) or en (English) |
zh |
SEARXNG_DEFAULT_LANGUAGE |
Default language code | - |
SEARXNG_BATCH_SIZE |
Servers to query per search (number or all) |
1 |
SEARXNG_MIN_SERVERS |
Merge results from top N fastest servers | 1 |
SEARXNG_DEFAULT_ENGINES |
Default engines (comma-separated) | Server default |
SEARXNG_DEFAULT_PAGES |
Default pages to fetch | 1 |
SEARXNG_DEFAULT_SAFESARCH |
Safe search level (0=off, 1=moderate, 2=strict) | Server default |
SEARXNG_MIN_INTERVAL |
Min interval between requests to same server (ms) | 450 |
SEARXNG_RESULT_FIELDS |
Fields included in result: url, title, summary, engine, sourceServer | All fields |
SEARXNG_VISIBLE_PARAMETERS |
Parameters visible to LLM | all |
Tool: search
Web search via SearXNG.
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
query |
string | Yes | Search query |
categories |
string | No | Categories: general, images, news, videos, science, it, etc. |
engines |
string | No | Engines: google, bing, duckduckgo, github, stackoverflow, etc. |
safesearch |
number | No | Level: 0=off, 1=moderate, 2=strict |
time_range |
string | No | Filter: day, week, month, year |
language |
string | No | Language code (e.g., en, zh) |
pages |
number | No | Pages to fetch |
startPage |
number | No | Starting page number |
Returns: Array of { url, title, summary, engine, sourceServer }
Publishing
npm version patch # or minor/major
git push --follow-tags
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.