MCP Catalogs
Homebrave-search-mcp screenshot

brave-search-mcp

by mikechao·117·Score 47

MCP server integrating Brave Search API with web, image, video, news, local POI, and LLM context search capabilities.

searchai-llmdeveloper-tools
18
Forks
0
Open issues
2 mo ago
Last commit
2d ago
Indexed

Overview

The brave-search-mcp is a comprehensive MCP server implementation that provides access to Brave Search API through multiple specialized tools. It offers six distinct search capabilities including traditional web search, image search, video search, news search, local points of interest search, and a specialized LLM context search that extracts and formats web content optimized for AI consumption. The server supports both stdio and HTTP modes with proper configuration options.

Try asking AI

After installing, here are 7 things you can ask your AI assistant:

you:Enhancing AI assistants with real-time web search capabilities
you:Research workflows requiring comprehensive web content extraction
you:Applications needing multi-modal search results (images, videos, news)
you:Local business information retrieval for service-based applications
you:Does this MCP server require authentication?
you:Can I use this server with ChatGPT?
you:What is the LLM context search feature?

When to choose this

Choose this when you need comprehensive search capabilities (web, images, news, local) integrated into your MCP-based AI workflows.

When NOT to choose this

Don't choose this if you need search results from multiple providers or have concerns about vendor lock-in with Brave's API.

Tools this server exposes

6 tools extracted from the README
  • brave_web_search

    Execute web searches using Brave's API

  • brave_image_search

    Get images from the web relevant to the query

  • brave_news_search

    Search the web for news articles, trending topics, or recent events

  • brave_local_search

    Search for local businesses, services, and points of interest

  • brave_video_search

    Search the web for videos

  • brave_llm_context_search

    Pre-extracted web content optimized for AI agents, LLM grounding, and RAG pipelines

Comparable tools

google-search-mcpduckduckgo-mcpbing-search-mcp

Installation

Installation

  1. Get a Brave Search API key from [Brave Search API account](https://brave.com/search/api/)

Using Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcp-servers": {
    "brave-search": {
      "command": "npx",
      "args": [
        "-y",
        "brave-search-mcp"
      ],
      "env": {
        "BRAVE_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Running as standalone

BRAVE_API_KEY="your_key_here" npx -y brave-search-mcp

For HTTP mode:

BRAVE_API_KEY="your_key_here" npx -y brave-search-mcp --http

FAQ

Does this MCP server require authentication?
Yes, you need to provide a Brave Search API key as an environment variable (BRAVE_API_KEY).
Can I use this server with ChatGPT?
Yes, the server supports ChatGPT through OpenAI Apps by running in HTTP mode and creating a local tunnel.
What is the LLM context search feature?
The LLM context search extracts and formats web content specifically optimized for AI consumption, with configurable parameters for token limits and snippet count.

Compare brave-search-mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.