This project provides an MCP server implementation for the Brave Search API, enabling developers to integrate comprehensive search functionalities—including web, local, image, video, news, and AI summarization—into their applications. It offers flexible transport options (STDIO/HTTP) and a standardized interface for accessing Brave's search capabilities.

How It Works

The server acts as a bridge between applications using the Model Context Protocol (MCP) and the Brave Search API. It processes search requests, forwards them to Brave's services, and returns structured results. Version 2.x refines response payloads, notably removing base64 image data for efficiency, and defaults to the STDIO transport for adherence to MCP conventions, though HTTP is configurable.

Quick Start & Requirements

Installation can be achieved via npx -y @smithery/cli install brave, Docker (docker.io/mcp/brave-search), or npx -y @brave/brave-search-mcp-server. Local development requires Node.js 22.x+ and npm. A Brave Search API key is mandatory, obtainable from the developer dashboard, with Free (2,000 queries/month) and Pro tiers available. Configuration is managed via environment variables (BRAVE_API_KEY is essential) or command-line arguments. Official documentation and integration examples for Claude Desktop and VS Code are provided.

Highlighted Details

• Comprehensive Toolset: Integrates brave_web_search, brave_local_search (Pro required for full features), brave_video_search, brave_image_search, brave_news_search, and brave_summarizer (AI-powered).
• Flexible Transports: Supports both STDIO (default) and HTTP communication protocols.
• Configurable Search: Offers extensive parameters for fine-tuning searches, including country, language, safesearch, freshness, result filtering, and AI summarization enablement.
• API Key Driven: Functionality is gated by a Brave Search API key, with different plans offering varying query limits and features.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or project roadmap are present in the provided README.

Licensing & Compatibility

The project is licensed under the permissive MIT License, allowing for free use, modification, and distribution, including in commercial and closed-source applications, provided the license terms are met.

Limitations & Caveats

Full local search capabilities and the extra_snippets feature require a Brave Search Pro plan. The image search response structure was updated in v2.x, removing base64-encoded image data.