Brave Search
OfficialMCP server for web and local search using Brave Search API.
claude mcp add --transport stdio modelcontextprotocol-server-brave-search npx -y @modelcontextprotocol/server-brave-search
How to use
The Brave Search MCP server enables developers to integrate web and local search functionalities into their applications using the Brave Search API. With this server, you can efficiently perform searches across the web and find local businesses and places, enhancing user experience with powerful search capabilities.
Once connected to the Brave Search MCP server, you can utilize the available tools: brave_web_search for conducting web searches and brave_local_search for finding local businesses. You can issue queries that include specific keywords, locations, or categories, allowing you to tailor the search results according to user needs. For optimal results, be sure to formulate queries that are concise and relevant to the information you seek.
How to install
Prerequisites
Ensure you have Node.js installed on your system. You can download it from nodejs.org.
Option A: Quick Start with npx
You can quickly start using the Brave Search MCP server with the following command:
npx -y @modelcontextprotocol/server-brave-search
Option B: Global Install Alternative
Alternatively, you can install the package globally using npm:
npm install -g @modelcontextprotocol/server-brave-search
After installation, you can start the server and begin utilizing its capabilities.
Additional notes
When configuring the Brave Search MCP server, be sure to set any necessary environment variables for API keys or other configurations as required by the Brave Search API. Common issues may arise from incorrect API key usage or network connectivity, so verify these elements if you encounter problems.
Available tools
brave_web_search
Performs a web search using Brave Search API
brave_local_search
Searches for local businesses and places
Related MCP Servers
aci
ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
ddgs
A metasearch library that aggregates results from diverse web search services
telegram
Telegram MCP server powered by Telethon to let MCP clients read chats, manage groups, and send/modify messages, media, contacts, and settings.
mcp-omnisearch
🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi), AI tools (Perplexity, FastGPT), and content processing services (Jina AI, Kagi). Combines search, AI responses, content processing, and enhancement features through a single interface.
lihil
2X faster ASGI web framework for python, offering high-level development, low-level performance.
hackmd
A Model Context Protocol server for integrating HackMD's note-taking platform with AI assistants.