Argus

Name: Argus
Author: Khamel83

@Khamel83

About Argus

One endpoint, five search providers. Argus routes queries across SearXNG, Brave, Serper, Tavily, and Exa with automatic fallback, RRF result ranking, health tracking, and budget enforcement. Extract clean text from any URL. Remember prior queries for smarter follow-ups. Zero exte

#search #web-search #extraction #mcp #python

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "argus": {
      "command": "argus",
      "args": [
        "mcp",
        "serve"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Argus?

Argus is a search aggregation server that routes queries across five search providers—SearXNG, Brave, Serper, Tavily, and Exa—with automatic fallback, RRF result ranking, health tracking, and budget enforcement. It also extracts clean text from any URL and remembers prior queries for smarter follow-ups. It uses SQLite as its only database and has no external dependencies. Argus is designed for developers and users who need resilient, multi-source search with cost control.

How to use Argus?

Connect to Argus via HTTP, CLI, MCP (Model Context Protocol), or Python import. The server exposes a single endpoint for all search operations.

Key features of Argus

One endpoint routing to five search providers
Automatic fallback between providers
RRF (Reciprocal Rank Fusion) result ranking
Health tracking for each provider
Budget enforcement per query or time period
Clean text extraction from any URL
Query memory for contextual follow-ups
Zero external database dependencies (SQLite only)

Use cases of Argus

Building a multi-provider search backend with graceful degradation
Enforcing cost limits on search API usage across teams
Aggregating and ranking results from multiple search engines
Extracting clean content from arbitrary URLs for analysis
Creating conversational search tools that remember prior queries

FAQ from Argus

Which search providers does Argus support?

Argus supports SearXNG, Brave, Serper, Tavily, and Exa, with automatic fallback between them.

What are Argus’s runtime dependencies?

Argus requires only SQLite as its database—no external database servers are needed.

How can I connect to Argus?

You can connect via HTTP, CLI, MCP (Model Context Protocol), or by importing it as a Python module.

Does Argus store my search queries?

Yes, Argus remembers prior queries in its SQLite database to enable smarter follow-ups. It does not require any external storage.

What authentication or transport protocols does Argus support?

—

Comments

More Search MCP servers

Tavily Mcp

tavily-ai

Production ready MCP server with real-time search, extract, map & crawl.

2.2K

Brave Search MCP Server

mikechao

An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Image Search, Video Search, News Search and LLM Context Search capabilities

121