What is an MCP Server?

MCP stands for Model Context Protocol. An MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools in a standardized way.

What is SearXNG and why is it used in this MCP Server?

SearXNG is a privacy-respecting metasearch engine. It's used because it doesn't track user queries or IP addresses, ensuring AI agents can search without compromising user privacy.

What are the prerequisites for installing the SearXNG MCP Server?

You need Python 3.9+, access to a running SearXNG instance, and optionally Docker, uv, or Smithery.

How do I install SearXNG?

The recommended way is via Docker. A sample `docker run` command is provided in the documentation.

What is uv and how do I use it for installation?

uv is a fast Python dependency management tool. You can install it with `pip install uv` and use it to install the server's dependencies.

What is Smithery and how do I use it for installation?

Smithery is a command-line tool for managing AI agent tools and MCP servers. You can install it using `pipx install smithery` (or another method described in Smithery's documentation) and then use it to install the SearXNG MCP server.

How do I configure the server?

Configuration is done via environment variables, which you can set in a `.env` file. Example `.env` files are provided.

What are the key environment variables I need to configure?

The key variables are `SEARXNG_BASE_URL` (the URL of your SearXNG instance), `HOST`, `PORT`, and `TRANSPORT` (which specifies whether to use SSE or stdio).

What are the different transport protocols (SSE and stdio)?

SSE (Server-Sent Events) and stdio are different ways the MCP server communicates with AI agents. SSE is typically used for running the server independently, while stdio allows the MCP client to spin up the server.

How do I run the server with SSE transport?

Set `TRANSPORT=sse` in your `.env` file and then run the server script (e.g., `uv run dev/searXNG-mcp/server.py`).

How do I integrate the server with an MCP client?

You need to configure your MCP client with the server's address (for SSE) or the command to run the server (for stdio). Example configurations are provided for different clients and setups.

What are the SearXNG search tool parameters?

These are parameters you can pass to the search tool to fine-tune your search queries. Examples include `q` (the query), `categories`, `engines`, and `language`.

Can I build my own MCP server based on this template?

Yes, this template provides a foundation for building more complex MCP servers. You can add your own tools, lifespan functions, prompts, and resources.

Where can I find more information about SearXNG?

See the [SearXNG documentation](https://docs.searxng.org/) for more details.

How does UBOS relate to the SearXNG MCP server?

UBOS is a full-stack AI Agent Development Platform that provides a broader ecosystem for AI agent development and deployment. The SearXNG MCP Server is available on the UBOS Asset Marketplace.

UBOS Asset Marketplace: Unleash the Power of Search with SearXNG MCP Server

In the rapidly evolving landscape of AI, the ability of AI agents to access and process information efficiently is paramount. The UBOS Asset Marketplace offers a robust solution to this challenge: the SearXNG MCP Server. This integration provides AI agents with powerful, privacy-respecting search capabilities, enabling them to perform comprehensive web searches and gather crucial data for informed decision-making.

What is the SearXNG MCP Server?

The SearXNG MCP Server is an implementation of the Model Context Protocol (MCP) server, integrated with SearXNG, a privacy-respecting metasearch engine. MCP is an open protocol standardizing how applications provide context to Large Language Models (LLMs). By acting as a bridge, the MCP server allows AI models to interact with external data sources, specifically leveraging SearXNG’s ability to aggregate search results from various search engines while maintaining user privacy.

Why SearXNG MCP Server? The Critical Need for Privacy-Respecting Search

In the era of data breaches and privacy concerns, integrating search capabilities into AI agents requires a cautious approach. Traditional search engines often track user data, raising ethical and security issues. SearXNG addresses these concerns by providing a metasearch engine that doesn’t track user queries or IP addresses. This ensures that AI agents can access information without compromising user privacy, making it an ideal solution for sensitive applications in healthcare, finance, and legal domains.

Key Features and Benefits

Privacy-Focused Search: Leverages SearXNG to ensure AI agents can perform web searches without compromising user privacy.
Seamless Integration: Follows Anthropic’s best practices for MCP server implementation, ensuring compatibility with any MCP-compatible client.
Customizable Search: Supports a wide range of SearXNG search parameters, allowing AI agents to fine-tune search queries for optimal results.
Flexible Deployment: Can be deployed using Docker, uv, or Smithery, offering flexibility for various infrastructure setups.
Easy Configuration: Uses environment variables for easy configuration of SearXNG base URL, host, port, and transport protocol.
Multiple Transport Options: Supports both SSE (Server-Sent Events) and stdio transport protocols for communication between the MCP server and AI agents.
Extensible Architecture: Provides a foundation for building more complex MCP servers with custom tools, lifespan functions, prompts, and resources.

Use Cases: Empowering AI Agents Across Industries

The SearXNG MCP Server unlocks a wide array of use cases for AI agents across various industries. Here are a few examples:

Financial Analysis: AI agents can use the server to gather real-time market data, news articles, and financial reports to make informed investment decisions.
Legal Research: Legal AI agents can perform comprehensive legal research, identifying relevant case law, statutes, and regulations.
Healthcare Diagnostics: AI agents can access medical literature, research papers, and clinical guidelines to assist in diagnosing and treating diseases.
Cybersecurity Threat Intelligence: AI agents can monitor online forums, dark web marketplaces, and threat intelligence feeds to identify emerging cybersecurity threats.
E-commerce Product Research: AI agents can analyze product reviews, pricing data, and competitor information to optimize product offerings and marketing strategies.
Content Creation: AI agents can research topics, gather information, and generate high-quality content for blog posts, articles, and social media campaigns.
Customer Support: AI agents can quickly find answers to customer queries, provide product information, and troubleshoot technical issues.

Installation and Configuration

The SearXNG MCP Server can be installed and configured using various methods, including Docker, uv, and Smithery. The installation process involves cloning the repository, installing dependencies, configuring environment variables, and running the server. Detailed instructions are provided for each installation method, ensuring a smooth setup process.

Using Docker

Docker provides a containerized deployment solution, ensuring consistency across different environments. To install the SearXNG MCP Server using Docker, you need to build the Docker image, create a .env file, and run the Docker image.

bash docker build -t mcp/searxng-mcp . docker run -d --env-file ./.env -p 32769:32769 mcp/searxng-mcp

Using uv

uv is a fast Python dependency management tool. To install the SearXNG MCP Server using uv, you need to install uv, clone the repository, install dependencies, and create a .env file.

bash pip install uv git clone https://github.com/The-AI-Workshops/searxng-mcp-server.git cd searxng-mcp-server/dev/searXNG-mcp uv pip install -r requirements.txt

Using Smithery

Smithery is a command-line tool for managing AI agent tools and MCP servers. To install the SearXNG MCP Server using Smithery, you need to install Smithery, install the SearXNG MCP server, and create a .env file.

bash

pipx install smithery #See Smithery documentation for various installation methods

smithery install @The-AI-Workshops/searxng-mcp-server

Configuration Options

The SearXNG MCP Server offers several configuration options that can be customized using environment variables. These variables include:

SEARXNG_BASE_URL: The base URL of your SearXNG instance.
HOST: The host to bind to when using SSE transport.
PORT: The port to listen on when using SSE transport.
TRANSPORT: The transport protocol (sse or stdio).

Integration with MCP Clients

Once the SearXNG MCP Server is running, it can be integrated with various MCP clients, such as Claude Desktop, Windsurf, and n8n. The integration process involves configuring the MCP client to connect to the SearXNG MCP Server using either SSE or stdio transport.

SSE Configuration

To connect to the SearXNG MCP Server using SSE transport, you need to configure the MCP client with the server’s URL.

{ “mcpServers”: { “searxng”: { “transport”: “sse”, “url”: “http://localhost:32769/sse” } } }

Stdio Configuration

To connect to the SearXNG MCP Server using stdio transport, you need to configure the MCP client with the server’s command, arguments, and environment variables.

{ “mcpServers”: { “searxng”: { “command”: “python”, “args”: [“dev/searXNG-mcp/server.py”], “env”: { “TRANSPORT”: “stdio”, “SEARXNG_BASE_URL”: “http://localhost:32768”, “HOST”: “0.0.0.0”, “PORT”: “32769” } } } }

Building Your Own Server: Extending the Capabilities

The SearXNG MCP Server serves as a template for building more complex MCP servers. Developers can add their own tools, lifespan functions, prompts, and resources to extend the server’s capabilities and tailor it to specific use cases. The @mcp.tool() decorator can be used to add custom tools, while the @mcp.resource() and @mcp.prompt() decorators can be used to add prompts and resources.

SearXNG Search Tool Parameters: Fine-Tuning Search Queries

The search tool supports a wide range of parameters that can be used to fine-tune search queries. These parameters include:

q: The search query string.
categories: Comma-separated list of active search categories.
engines: Comma-separated list of active search engines.
language: Code of the language.
page: Search page number.
time_range: Search within day, month, or year.
format: Result format (json, csv, rss).
safesearch: Safe search level.

UBOS: The Foundation for AI Agent Development

The UBOS Asset Marketplace is part of a broader ecosystem designed to facilitate AI agent development and deployment. UBOS provides a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. Our platform helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.

By leveraging the UBOS platform, organizations can streamline the development, deployment, and management of AI agents, accelerating their adoption and maximizing their impact. The UBOS Asset Marketplace, with its SearXNG MCP Server offering, provides a crucial component for empowering AI agents with reliable, privacy-respecting search capabilities.

Conclusion: Empowering AI Agents with Privacy and Precision

The SearXNG MCP Server available on the UBOS Asset Marketplace offers a powerful solution for integrating privacy-respecting search capabilities into AI agents. By leveraging SearXNG’s metasearch engine, AI agents can access information without compromising user privacy, making it an ideal solution for sensitive applications. With its flexible deployment options, easy configuration, and extensible architecture, the SearXNG MCP Server empowers organizations to build more intelligent, secure, and responsible AI agents.

Embrace the future of AI with the SearXNG MCP Server and unlock the full potential of your AI agents with UBOS.