mcpField
S
Saaros-MCP-Server

Saaros-MCP-Server

Local
github.com/mjochum64Search0Updated 80w ago
Repository

About Saaros-MCP-Server

Saaros-MCP-Server connects MCP clients to the Brave Search API for web searches. It runs as a background Python thread, uses JSON-RPC 2.0 over stdin/stdout, and supports rate limiting.

Key features

  1. 01Brave Search API integration
  2. 02Background-thread operation
  3. 03JSON-RPC 2.0 communication
  4. 04Rate limiting support

Use cases

  1. 01Searching the web with Brave Search
  2. 02Embedding the server in a larger application

MCP support

The MCP server exposes Brave Search through tools such as `brave_web_search`. MCP clients communicate with it over stdin/stdout using JSON-RPC 2.0.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Saaros-MCP-Server

A Model Context Protocol (MCP) server that provides access to the Brave Search API, running as a background thread.

Features

  • Runs as a background thread
  • Implements JSON-RPC 2.0 protocol
  • Rate limiting support
  • Brave Search API integration

Setup

  1. Set up your Brave Search API key:
    • Get an API key from Brave Search API
    • Create a .env file in the project root: 
      BRAVE_API_KEY=your_api_key_here

Usage

The server communicates via stdin/stdout using the JSON-RPC 2.0 protocol. Here are example requests:

  1. List available tools:
{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "listTools",
    "params": {}
}
  1. Perform a web search:
{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "callTool",
    "params": {
        "name": "brave_web_search",
        "arguments": {
            "query": "your search query",
            "count": 10
        }
    }
}

To run the server:

uv run main.py

Development

The server is implemented as a Python thread, making it suitable for integration into larger applications. The main components are:

  • MCPServer: The main server class that runs in a background thread
  • BraveSearchConfig: Configuration class for API settings
  • Request/response queues for thread-safe communication

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.