back to home

brave / brave-search-mcp-server

777 stars
140 forks
21 issues
TypeScriptDockerfileJavaScript

AI Architecture Analysis

This repository is indexed by RepoMind. By analyzing brave/brave-search-mcp-server in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.

Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.

Source files are only loaded when you start an analysis to optimize performance.

Embed this Badge

Showcase RepoMind's analysis directly in your repository's README.

[![Analyzed by RepoMind](https://img.shields.io/badge/Analyzed%20by-RepoMind-4F46E5?style=for-the-badge)](https://repomind.in/repo/brave/brave-search-mcp-server)
Preview:Analyzed by RepoMind

Repository Overview (README excerpt)

Crawler view

Brave Search MCP Server An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, image search, video search, news search, and AI-powered summarization. This project supports both STDIO and HTTP transports, with STDIO as the default mode. Migration 1.x to 2.x Default transport now STDIO To follow established MCP conventions, the server now defaults to STDIO. If you would like to continue using HTTP, you will need to set the environment variable to , or provide the runtime argument when launching the server. Response structure of Version 1.x of the MCP server would return base64-encoded image data along with image URLs. This dramatically slowed down the response, as well as consumed unnecessarily context in the session. Version 2.x removes the base64-encoded data, and returns a response object that more closely reflects the original Brave Search API response. The updated output schema is defined in . Tools Web Search ( ) Performs comprehensive web searches with rich result types and advanced filtering options. **Parameters:** • (string, required): Search terms (max 400 chars, 50 words) • (string, optional): Country code (default: "US") • (string, optional): Search language (default: "en") • (string, optional): UI language (default: "en-US") • (number, optional): Results per page (1-20, default: 10) • (number, optional): Pagination offset (max 9, default: 0) • (string, optional): Content filtering ("off", "moderate", "strict", default: "moderate") • (string, optional): Time filter ("pd", "pw", "pm", "py", or date range) • (boolean, optional): Include highlighting markers (default: true) • (boolean, optional): Enable spell checking (default: true) • (array, optional): Filter result types (default: ["web", "query"]) • (array, optional): Custom re-ranking definitions • (string, optional): Measurement units ("metric" or "imperial") • (boolean, optional): Get additional excerpts (Pro plans only) • (boolean, optional): Enable summary key generation for AI summarization Local Search ( ) Searches for local businesses and places with detailed information including ratings, hours, and AI-generated descriptions. **Parameters:** • Same as with automatic location filtering • Automatically includes "web" and "locations" in result_filter **Note:** Requires Pro plan for full local search capabilities. Falls back to web search otherwise. Video Search ( ) Searches for videos with comprehensive metadata and thumbnail information. **Parameters:** • (string, required): Search terms (max 400 chars, 50 words) • (string, optional): Country code (default: "US") • (string, optional): Search language (default: "en") • (string, optional): UI language (default: "en-US") • (number, optional): Results per page (1-50, default: 20) • (number, optional): Pagination offset (max 9, default: 0) • (boolean, optional): Enable spell checking (default: true) • (string, optional): Content filtering ("off", "moderate", "strict", default: "moderate") • (string, optional): Time filter ("pd", "pw", "pm", "py", or date range) Image Search ( ) Searches for images with automatic fetching and base64 encoding for direct display. **Parameters:** • (string, required): Search terms (max 400 chars, 50 words) • (string, optional): Country code (default: "US") • (string, optional): Search language (default: "en") • (number, optional): Results per page (1-200, default: 50) • (string, optional): Content filtering ("off", "strict", default: "strict") • (boolean, optional): Enable spell checking (default: true) News Search ( ) Searches for current news articles with freshness controls and breaking news indicators. **Parameters:** • (string, required): Search terms (max 400 chars, 50 words) • (string, optional): Country code (default: "US") • (string, optional): Search language (default: "en") • (string, optional): UI language (default: "en-US") • (number, optional): Results per page (1-50, default: 20) • (number, optional): Pagination offset (max 9, default: 0) • (boolean, optional): Enable spell checking (default: true) • (string, optional): Content filtering ("off", "moderate", "strict", default: "moderate") • (string, optional): Time filter (default: "pd" for last 24 hours) • (boolean, optional): Get additional excerpts (Pro plans only) • (array, optional): Custom re-ranking definitions Summarizer Search ( ) Generates AI-powered summaries from web search results using Brave's summarization API. **Parameters:** • (string, required): Summary key from web search results (use in web search) • (boolean, optional): Include entity information (default: false) • (boolean, optional): Add source URL references (default: false) **Usage:** First perform a web search with , then use the returned summary key with this tool. Configuration Getting an API Key • Sign up for a Brave Search API account • Choose a plan: • **Free**: 2,000 queries/month, basic web search • **Pro**: Enhanced features including local search, AI summaries, extra snippets • Generate your API key from the developer dashboard Environment Variables The server supports the following environment variables: • : Your Brave Search API key (required) • : Transport mode ("http" or "stdio", default: "stdio") • : HTTP server port (default: 8000) • : HTTP server host (default: "0.0.0.0") • : Desired logging level("debug", "info", "notice", "warning", "error", "critical", "alert", or "emergency", default: "info") • : When used, specifies a whitelist for supported tools • : When used, specifies a blacklist for supported tools • : HTTP stateless mode (default: "true"). When running on Amazon Bedrock Agentcore, set to "true". Command Line Options Installation Installing via Smithery To install Brave Search automatically via Smithery: Usage with Claude Desktop Add this to your : Docker NPX Usage with VS Code For quick installation, use the one-click installation buttons below…