SearXNG MCP Server
A web search server powered by the SearXNG API.
SearXNG MCP Server
An MCP server implementation that integrates the SearXNG API, providing web search capabilities.
Features
- Web Search: General queries, news, articles, with pagination.
- Pagination: Control which page of results to retrieve.
- Time Filtering: Filter results by time range (day, month, year).
- Language Selection: Filter results by preferred language.
- Safe Search: Control content filtering level for search results.
Tools
-
searxng_web_search
- Execute web searches with pagination
- Inputs:
query(string): The search query. This string is passed to external search services.pageno(number, optional): Search page number, starts at 1 (default 1)time_range(string, optional): Filter results by time range - one of: "day", "month", "year" (default: none)language(string, optional): Language code for results (e.g., "en", "fr", "de") or "all" (default: "all")safesearch(number, optional): Safe search filter level (0: None, 1: Moderate, 2: Strict) (default: instance setting)
-
web_url_read
- Read and convert the content from a URL to markdown
- Inputs:
url(string): The URL to fetch and process
Configuration
Setting the SEARXNG_URL
- Choose a SearxNG instance from the list of public instances or use your local environment.
- Set the
SEARXNG_URLenvironment variable to the instance URL. - The default
SEARXNG_URLvalue ishttp://localhost:8080.
Using Authentication
If you are using a password protected SearxNG instance you can set a username and password for HTTP Basic Auth:
- Set the
AUTH_USERNAMEenvironmental variable to your username - Set the
AUTH_PASSWORDenvironmental variable to your password
Usage with Claude Desktop
NPX
{
"mcpServers": {
"searxng": {
"command": "npx",
"args": [
"-y",
"mcp-searxng"
],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
NPM
npm install -g mcp-searxng
And then in your MCP config file:
{
"mcpServers": {
"searxng": {
"command": "mcp-searxng",
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
Docker
Using Pre-built Image from Docker Hub
docker pull isokoliuk/mcp-searxng:latest
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"searxng": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"SEARXNG_URL",
"isokoliuk/mcp-searxng:latest"
],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
Build Locally
docker build -t mcp-searxng:latest -f Dockerfile .
Use
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"searxng": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"SEARXNG_URL",
"mcp-searxng:latest"
],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Verwandte Server
Web3 Research MCP
A free and local tool for in-depth crypto research.
Unified Docs Hub
Creates a massive, searchable knowledge base from numerous curated and auto-discovered GitHub projects.
Carity MCP Server
Retrieve relevant data chunks from the Carity API based on search queries.
Google Search Engine
A server for Google search and webpage content extraction, built on Cloudflare Workers with OAuth support.
Deep Research
A server for conducting deep research and generating reports.
MCP Omnisearch
Unified access to multiple search providers and AI tools like Tavily, Perplexity, Kagi, Jina AI, Brave, and Firecrawl.
Search MCP Server
A server providing web and similarity search functionalities, designed for Claude Desktop. It requires external embedding and API services.
AI Book Agent MCP Server
Provides AI assistants with intelligent access to ML textbook content for creating accurate, source-grounded documentation.
MCP Research Friend
Research tools, including a Sqlite-backed document stash
search-scrape
Self-hosted Stealth Scraping & Federated Search for AI Agents. A 100% private, free alternative to Firecrawl, Jina Reader, and Tavily. Featuring Universal Anti-bot Bypass + Semantic Research Memory, Copy-Paste setup