Brave Search MCP server

Retrieve web pages, news, and local business results via Brave API.
Back to servers
Provider
Anthropic
Release date
Nov 19, 2024
Language
TypeScript
Package
Stats
181.6K downloads
42.6K stars

The Brave Search MCP Server integrates the Brave Search API with Model Context Protocol, providing both web and local search capabilities. This server enables AI assistants to perform searches for general queries, news, local businesses, and services with advanced filtering options.

Features

  • Web Search: Execute general queries, news, and article searches with pagination and freshness controls
  • Local Search: Find businesses, restaurants, and services with detailed information
  • Flexible Filtering: Control result types, safety levels, and content freshness
  • Smart Fallbacks: Local search automatically falls back to web search when no results are found

Installation

Getting an API Key

Before installing, you'll need to obtain a Brave Search API key:

  1. Sign up for a Brave Search API account
  2. Choose a plan (Free tier available with 2,000 queries/month)
  3. Generate your API key from the developer dashboard

Installation with Claude Desktop

Add the following configuration to your claude_desktop_config.json file:

Using Docker

{
  "mcpServers": {
    "brave-search": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "BRAVE_API_KEY",
        "mcp/brave-search"
      ],
      "env": {
        "BRAVE_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Using NPX

{
  "mcpServers": {
    "brave-search": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-brave-search"
      ],
      "env": {
        "BRAVE_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Installation with VS Code

For manual installation in VS Code, add the following configuration to your User Settings (JSON) file. Access this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).

Using Docker

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "brave_api_key",
        "description": "Brave Search API Key",
        "password": true
      }
    ],
    "servers": {
      "brave-search": {
        "command": "docker",
        "args": [
          "run",
          "-i",
          "--rm",
          "-e",
          "BRAVE_API_KEY",
          "mcp/brave-search"
        ],
        "env": {
          "BRAVE_API_KEY": "${input:brave_api_key}"
        }
      }
    }
  }
}

Using NPX

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "brave_api_key",
        "description": "Brave Search API Key",
        "password": true
      }
    ],
    "servers": {
      "brave-search": {
        "command": "npx",
        "args": ["-y", "@modelcontextprotocol/server-brave-search"],
        "env": {
          "BRAVE_API_KEY": "${input:brave_api_key}"
        }
      }
    }
  }
}

Alternatively, you can add this configuration to a file called .vscode/mcp.json in your workspace to share it with others. Note that the mcp key is not needed in the .vscode/mcp.json file.

Using the MCP Server

Once installed, you can use the following tools through your AI assistant:

Web Search

Use the brave_web_search tool to perform web searches:

  • Inputs:
    • query (string): Your search terms
    • count (number, optional): Results per page (maximum 20)
    • offset (number, optional): Pagination offset (maximum 9)

Local Search

Use the brave_local_search tool to find local businesses and services:

  • Inputs:
    • query (string): Local search terms (e.g., "coffee shops in Boston")
    • count (number, optional): Number of results (maximum 20)

The local search will automatically fall back to web search if no local results are found.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later