mcp-searxng
Integrates SearXNG API to give AI assistants web search and URL reading capabilities.
README
SearXNG MCP Server
An MCP server that integrates the SearXNG API, giving AI assistants web search and URL reading capabilities.
Quick Start
Requires Bun.
Add the server to your MCP client configuration:
{
"mcpServers": {
"searxng": {
"command": "bunx",
"args": ["@tterrasson/mcp-searxng"],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
Replace YOUR_SEARXNG_INSTANCE_URL with the URL of your SearXNG instance, for example https://search.example.com.
Features
- Web Search: General queries, news, articles, with pagination.
- URL Content Reading: Content extraction powered by Readability (Firefox Reader Mode). Strips navigation, ads, and boilerplate before converting to Markdown, with pagination, section filtering, and heading extraction.
- Pagination: Control which page of results to retrieve.
- Time Filtering: Filter results by time range: day, month, or year.
- Language Selection: Filter results by preferred language.
- Safe Search: Control the search result filtering level.
- Category Filtering: Restrict results to specific engine types (news, images, science, etc.).
How It Works
mcp-searxng is a standalone MCP server that runs with Bun. Your AI assistant connects to it through the MCP protocol, and the server queries any SearXNG instance through its HTTP JSON API.
Not a SearXNG plugin: This project cannot be installed as a native SearXNG plugin. Point it at an existing SearXNG instance by setting
SEARXNG_URL.
AI Assistant
| MCP protocol
v
mcp-searxng (this project, Bun process)
| HTTP JSON API (SEARXNG_URL)
v
SearXNG instance
Tools
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 ofday,month,year.language(string, optional): Language code for results, for exampleen,fr,de, orall. Default:all.safesearch(number, optional): Safe search filter level, where0is none,1is moderate, and2is strict. Defaults to the SearXNG instance setting.categories(string, optional): Comma-separated list of search categories to filter results by engine type. Available values:general,images,videos,news,map,music,it,science,files,social media. Defaults to the SearXNG instance setting.
web_url_read
Read and convert the content from a URL to Markdown.
Inputs:
url(string): The URL to fetch and process.startChar(number, optional): Starting character position for content extraction. Default:0.maxLength(number, optional): Maximum number of characters to return.section(string, optional): Extract content under a specific heading.readHeadings(boolean, optional): Return only a list of headings instead of full content.
Installation
This fork is intended to run with Bun.
git clone https://github.com/tterrasson/mcp-searxng.git
cd mcp-searxng
bun install
bun run build
Use bun dist/index.js in MCP clients after building.
For local development, you can run the TypeScript entrypoint directly:
SEARXNG_URL=http://localhost:8080 bun src/index.ts
HTTP Transport
By default the server uses STDIO. Set MCP_HTTP_PORT to enable HTTP mode:
{
"mcpServers": {
"searxng-http": {
"command": "bun",
"args": ["/absolute/path/to/mcp-searxng/dist/index.js"],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
"MCP_HTTP_PORT": "3000"
}
}
}
}
Endpoints:
POST/GET/DELETE /mcp: MCP protocolGET /health: health check
Run it locally:
MCP_HTTP_PORT=3000 SEARXNG_URL=http://localhost:8080 bun dist/index.js
curl http://localhost:3000/health
Configuration
Set SEARXNG_URL to your SearXNG instance URL. All other variables are optional.
Client compatibility (PLAIN_TEXT_CONTENT)
By default, web_search returns results only via structuredContent (the MCP structured data field). Clients that do not support structuredContent — such as LM Studio — will see an empty response.
Set PLAIN_TEXT_CONTENT to any non-empty value to also include results as plain text in the standard content field:
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
"PLAIN_TEXT_CONTENT": "true"
}
Full environment variable reference: CONFIGURATION.md
Troubleshooting
403 Forbidden from SearXNG
Your SearXNG instance likely has JSON format disabled. Edit settings.yml, usually /etc/searxng/settings.yml:
search:
formats:
- html
- json
Restart your SearXNG service, then verify:
curl 'http://localhost:8080/search?q=test&format=json'
You should receive a JSON response. If not, confirm the file is correctly loaded and YAML indentation is valid.
See also: SearXNG settings docs and SearXNG discussion #1789.
Development
bun install
bun run build
bun run lint
bun test tests
Use the MCP inspector:
bun run inspector
Contributing
See CONTRIBUTING.md.
License
MIT. See LICENSE for details.
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.