SearXNG Mul MCP logo

SearXNG Mul MCP

Community
jae-jae

A Model Context Protocol (MCP) server for SearXNG search engine with multi-query parallel search support

Publisherjae-jae
Repositorysearxng-mul-mcp
LanguageTypeScript
Forks
7
Stars
99
Available tools
0
Transport typestdio, streamable-http
Categories
Licensenull
Links
  • Connect tools to AI workflows

    SearXNG Mul MCP exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    99 stars and 7 forks from the linked repository.

中文 | Deutsch | English | Español | français | 日本語 | 한국어 | Português | Русский

SearXNG Mul MCP

A Model Context Protocol (MCP) server for SearXNG metasearch engine integration, supporting multi-query parallel search with both stdio and HTTP transport protocols.

🌟 Recommended: OllaMan - Powerful Ollama AI Model Manager.

Features

  • Multi-Query Parallel Search: Execute multiple search queries simultaneously for improved efficiency
  • Dual Transport Support: Compatible with both stdio and HTTP MCP transport protocols
  • SearXNG API Integration: Direct integration with SearXNG REST API without browser automation
  • Basic Authentication: Support for SearXNG servers with Basic Auth protection
  • Docker Deployment: Complete containerization with Docker and Docker Compose
  • Environment Configuration: Flexible configuration management through environment variables

Quick Start

NPM Usage

Stdio Mode (Default)

bash
SEARXNG_URL=https://your.searxng.com npx -y searxng-mul-mcp

HTTP Mode

bash
SEARXNG_URL=https://your.searxng.com npx -y searxng-mul-mcp --transport=http --host=0.0.0.0 --port=3000

Environment Variables

bash
# Required: SearXNG server URL
SEARXNG_URL=https://your.searxng.com

# Optional: Basic Auth credentials
USERNAME=your_username
PASSWORD=your_password

# Optional: Transport configuration (can also use CLI flags)
TRANSPORT=stdio|http
HOST=0.0.0.0        # HTTP mode only
PORT=3000           # HTTP mode only

# Optional: Debug mode
DEBUG=false

Configuration

Claude Desktop Configuration

Add the following configuration to your Claude Desktop claude_desktop_config.json file:

stdio mode:

json
{
  "mcpServers": {
    "searxng-mul-mcp": {
      "command": "npx",
      "args": ["-y", "searxng-mul-mcp"],
      "env": {
        "SEARXNG_URL": "https://your.searxng.com",
        "USERNAME": "your_username",
        "PASSWORD": "your_password"
      }
    }
  }
}

SearXNG Server Setup

This MCP server requires access to a SearXNG instance. You can:

  1. Use a public SearXNG instance (like https://your.searxng.com)
  2. Deploy your own SearXNG server
  3. Use a private SearXNG instance with Basic Auth

Basic Authentication

If your SearXNG server requires Basic Auth:

bash
export USERNAME=your_username
export PASSWORD=your_password

Transport Protocols

Stdio Transport

  • Default mode for MCP client integration
  • Uses standard input/output for communication
  • Suitable for direct MCP client connections

HTTP Transport

  • Provides StreamableHTTP JSON-RPC interface (protocol version 2025-03-26)
  • Includes health check endpoint at /health
  • MCP endpoint at /mcp for client communication
  • Supports session management with automatic cleanup
  • Full CORS support for cross-origin requests
  • Suitable for web-based integrations and modern MCP clients

Installation

From Source

bash
git clone <repository-url>
cd searxng-mul-mcp
npm install
npm run build
npm start

Docker Deployment

Create a docker-compose.yml file:

yaml
services:
  searxng-mul-mcp:
    image: ghcr.io/jae-jae/searxng-mul-mcp:latest
    environment:
      - SEARXNG_URL=https://your.searxng.com
      # Optional: Basic Auth
      # - USERNAME=your_username
      # - PASSWORD=your_password
    ports:
      - "3000:3000"

Run with:

bash
docker-compose up -d

MCP Tool Usage

The server provides a single search tool that accepts the following parameters:

Parameters

  • queries (required): Array of search query strings to execute in parallel
  • engines (optional): Specific search engines to use (e.g., "google", "bing", "duckduckgo")
  • categories (optional): Search categories to filter results (e.g., "general", "images", "news")
  • safesearch (optional): Safe search level (0=off, 1=moderate, 2=strict)
  • language (optional): Search language code (e.g., "en", "zh", "es")

Development

Prerequisites

  • Node.js 18 or higher
  • npm or yarn
  • TypeScript

Build Commands

bash
# Install dependencies
npm install

# Build TypeScript
npm run build

# Start development server
npm run dev

# Run in production
npm start

# Clean build directory
npm run clean

# Run tests
npm test

# Lint code
npm run lint

# Format code
npm run format

Project Structure

searxng-mul-mcp/
├── src/
│   ├── index.ts                 # Application entry point
│   ├── server.ts               # MCP server core logic
│   ├── config/
│   │   └── index.ts            # Configuration management
│   ├── tools/
│   │   ├── index.ts            # Tool definitions
│   │   └── searxng.ts          # SearXNG search tool implementation
│   ├── transports/
│   │   ├── index.ts            # Transport factory
│   │   ├── stdio.ts            # Stdio transport implementation
│   │   ├── http.ts             # HTTP transport implementation
│   │   └── types.ts            # Transport type definitions
│   ├── services/
│   │   └── searxng-api.ts      # SearXNG API client
│   └── utils/
│       └── logger.ts           # Logging utilities
├── build/                      # TypeScript compilation output
├── package.json               # Project dependencies and scripts
├── tsconfig.json              # TypeScript configuration
├── Dockerfile                 # Docker image build
├── docker-compose.yml         # Docker Compose configuration
└── README.md                  # This file

API Reference

SearXNG API Integration

This server integrates with the SearXNG search API. For more information about SearXNG API capabilities, see: https://docs.searxng.org/dev/search_api.html

Error Handling

The server implements comprehensive error handling:

  • Network errors: Automatic retry mechanism (up to 3 attempts)
  • Authentication errors: Clear error messages for auth failures
  • API rate limiting: Graceful degradation and error reporting
  • Timeout handling: Configurable request timeout (default: 30 seconds)

Monitoring

Health Checks

HTTP mode provides a health check endpoint:

bash
curl http://localhost:3000/health

Response:

json
{
  "status": "healthy",
  "timestamp": "2024-01-01T00:00:00.000Z",
  "version": "1.0.0"
}

Logging

The server provides structured logging with configurable levels:

  • ERROR: Critical errors and failures
  • WARN: Warning messages and degraded functionality
  • INFO: General operational information
  • DEBUG: Detailed debugging information (enable with DEBUG=true)

Troubleshooting

Common Issues

  1. Connection Failed: Check your SEARXNG_URL and network connectivity
  2. Authentication Error: Verify USERNAME and PASSWORD for Basic Auth
  3. Port Already in Use: Change the PORT environment variable for HTTP mode
  4. Search Timeout: Increase timeout or check SearXNG server performance

Debug Mode

Enable debug logging for detailed troubleshooting:

bash
DEBUG=true npx searxng-mul-mcp

License

MIT License - see LICENSE file for details.

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

Support

For issues and questions:

  1. Check the troubleshooting section
  2. Review SearXNG documentation
  3. Open an issue on GitHub

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "jae-jae-searxng-mul-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "searxng-mul-mcp"
      ]
    }
  }
}

Use SearXNG Mul MCP MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once SearXNG Mul MCP is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. You can run MCP locally on your device or connect to a remote MCP server URL.

Option 1: Use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add SearXNG Mul MCP as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the SearXNG Mul MCP MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "jae-jae-searxng-mul-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "searxng-mul-mcp"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the SearXNG Mul MCP MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the SearXNG Mul MCP MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use SearXNG Mul MCP to help me with this task?
SearXNG Mul MCP
Sure. I read it.
Here is what I found using SearXNG Mul MCP.

Option 2: Add an MCP server URL

Use this when SearXNG Mul MCP is already hosted remotely or your team wants one shared connector that multiple users can access.

1

Open MCP connectors

In TypingMind, go to Plugins, open MCP connectors, then choose Add URL.

  1. Open TypingMind in your browser.
  2. Go to Plugins.
  3. Open MCP connectors.
  4. Click Add URL.
TypingMind Add Custom MCP Server URL form
2

Paste the server URL

Enter your server URL in the Server URL field. Add a connection name, description, icon, custom HTTP headers, or OAuth client settings if the server requires them.

  1. Paste your server URL into the Server URL field.
  2. Enter a connection name for SearXNG Mul MCP.
  3. Add a description and icon if you want it to be easier to identify.
  4. Add custom HTTP headers or OAuth client details if the server requires authentication.
3

Create the connection

Click Create connection, then return to the Plugins list and confirm the new MCP connection is active.

  1. Click Create connection.
  2. Return to the MCP connectors list.
  3. Confirm the SearXNG Mul MCP connection appears as active.
  4. Refresh the plugin list if the connection does not appear immediately.
4

Switch models without reconnecting

Start a chat with your preferred model, enable the SearXNG Mul MCP tools from Plugins, and switch to another model whenever needed. The MCP connection stays available to the TypingMind workspace.

  1. Start a new chat in TypingMind.
  2. Select the AI model you want to use.
  3. Enable the SearXNG Mul MCP tools from Plugins.
  4. Ask the model to use the tool when needed.
  5. Switch to another AI model and reuse the same MCP connection.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use SearXNG Mul MCP to help me with this task?
SearXNG Mul MCP
Sure. I read it.
Here is what I found using SearXNG Mul MCP.

Frequently asked questions

What is the SearXNG Mul MCP MCP server used for?

SearXNG Mul MCP is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use SearXNG Mul MCP MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use SearXNG Mul MCP with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use SearXNG Mul MCP MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With SearXNG Mul MCP connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect SearXNG Mul MCP MCP to TypingMind?

SearXNG Mul MCP can be connected in TypingMind with the local MCP connector or by adding a remote MCP server URL. Use the local connector when the server needs access to files, apps, or private resources on your device, and use a server URL when the MCP server is hosted remotely.

What tools does SearXNG Mul MCP MCP provide in TypingMind?

SearXNG Mul MCP exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use SearXNG Mul MCP MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If SearXNG Mul MCP requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇