RustXNG
RustXNG is a self-hosted search engine that gives AI agents web search results and page text through a JSON API or MCP, for developers.
What it is good for
- Giving an AI agent web search without a paid search service
- Fetching readable text from web pages for an AI assistant
- Keeping search queries on a server you run yourself
- Searching a local index of selected sites and Wikipedia
At a glance
- Who it is for
- Setup difficulty
- Technical ยท Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- MCP server or connector
- Tasks
- Works with
- SearXNG, Wikipedia, Docker, Exa Search
How to get started with RustXNG
- Download a release binary for Linux, macOS or Windows, and check its SHA-256 file, or install with Cargo.
- Start a local server with
rustxng --bind 127.0.0.1 --port 29483. - Run a test search with curl against
http://127.0.0.1:29483/searchusingformat=json. - Start the MCP server for your AI app with
rustxng mcp.
From the project's own documentation. If a step does not match what you see, the official pages have the latest instructions.
Before you try it
- Source installation needs Rust 1.89 or newer and a C build toolchain.
- Standard and Full profiles send your queries to external search providers, even when run locally.
- Full profile includes providers whose terms may forbid automated access; Exa is billed and needs an API key.
- PDF text needs Poppler, and JavaScript-heavy pages need an optional Firefox renderer.
Momentum
- Rank this week
- Not ranked (last #85, week 45, 2026)
- Best rank
- #85 week 45, 2026
- GitHub stars
- 977
GitHub numbers as of Nov 16, 2026. Updated weekly.
Ranking history
Questions
- Is RustXNG free?
- Yes. It is free and open source (AGPL-3.0 license).
- Do I need to know how to code to use RustXNG?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does RustXNG work with?
- According to its own documentation, it works with SearXNG, Wikipedia, Docker, and Exa Search.
- How do I get started with RustXNG?
- 1. Download a release binary for Linux, macOS or Windows, and check its SHA-256 file, or install with Cargo. 2. Start a local server with rustxng --bind 127.0.0.1 --port 29483. 3. Run a test search with curl against http://127.0.0.1:29483/search using format=json. 4. Start the MCP server for your AI app with rustxng mcp.
- What should I know before trying RustXNG?
- Source installation needs Rust 1.89 or newer and a C build toolchain. Standard and Full profiles send your queries to external search providers, even when run locally. Full profile includes providers whose terms may forbid automated access; Exa is billed and needs an API key. PDF text needs Poppler, and JavaScript-heavy pages need an optional Firefox renderer.
- What is RustXNG good for?
- Giving an AI agent web search without a paid search service, fetching readable text from web pages for an AI assistant, keeping search queries on a server you run yourself, and searching a local index of selected sites and Wikipedia.
Similar agents to RustXNG
- Argo
A search tool for agents covering 284 sources, rather than a self-hosted engine built on SearXNG.
- webclaw
Focuses on turning websites into clean markdown or JSON rather than metasearch across providers.
- crawl4ai
A hosted scraping and search API that returns Markdown or structured data, not a self-run metasearch engine.
- paper-search-mcp
Searches only academic paper sources instead of general web search.
- stealth-browser-mcp
Controls a real browser for sites that block automation, rather than querying search providers.
- Financial-API
Financial-API is an official A-share market data service that gives AI agents live and historical stock, fund, and index data.