MCP Connector

Search the web and find local businesses with Brave

MCP server for the Brave Search API: web and local business search with pagination and freshness filters.

Works with brave

46
Spark score
out of 100
Updated May 2025
Source checked Sep 10, 2026
Version 1.0.0

Add to Favorites

Why it matters

Enable AI assistants to perform real-time web searches and local business lookups through the Brave Search API, providing fresh, filtered results with pagination controls and automatic fallback handling.

Outcomes

What it gets done

01

Execute web searches with customizable result counts and pagination offsets

02

Find local businesses, restaurants, and services with detailed information

03

Filter search results by content type, safety level, and freshness

04

Automatically fall back to web search when local results are unavailable

Source

Get it from source

Spark does not host a copy of it.

Open source

Reports

Agent outcome reports

No reports yet

Overview

Brave Search

This MCP server connects an AI assistant to the Brave Search API for web search with pagination and freshness filtering, and local business search with automatic web fallback. Use it when an assistant needs current web results or local business lookups; the repository sits in MCP's archived servers collection, so check for an actively maintained alternative before long-term adoption.

What it does

This MCP server integrates the Brave Search API to give an AI assistant both web and local search. brave_web_search runs general web queries - news, articles, and general information - with pagination (up to 20 results per page, offset up to 9) and content-freshness/safety filtering. brave_local_search looks up businesses, restaurants, and services with detailed information, accepting a query and an optional result count (also capped at 20), and automatically falls back to a web search when no local results are found - so a single tool call covers both cases without the caller needing to know in advance which search type will succeed.

When to use - and when NOT to

Use it when an assistant needs to answer questions with current web information or find local businesses and services with structured detail, rather than relying only on a model's training data. It requires a Brave Search API key - a free tier is available at 2,000 queries per month, with paid plans for higher volume, obtained by signing up for a Brave Search API account and generating a key from the developer dashboard. Note that this repository lives in the Model Context Protocol project's archived servers collection rather than its actively maintained one, so treat it as a reference implementation and check whether a currently maintained fork or successor better fits a new integration before committing to it long-term.

Capabilities

  • Web search with pagination (count, offset) and freshness/safety filtering
  • Local business and service search with automatic fallback to web search when no local results exist
  • Flexible result-type and content-freshness controls across both tools

How to install

Get a Brave Search API key by signing up at the Brave Search API site and generating a key from the developer dashboard (free tier: 2,000 queries/month). Then configure your MCP client, for example via NPX:

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

A Docker variant is also available (docker run -i --rm -e BRAVE_API_KEY mcp/brave-search), built from the project's own Dockerfile (docker build -t mcp/brave-search:latest -f src/brave-search/Dockerfile .). VS Code supports the same NPX or Docker configuration through its own MCP settings, prompting for the API key as a secret input rather than hardcoding it, and the server is distributed under the MIT License.

Who it's for

Developers building an assistant that needs live web search results or local business lookups - research assistants, customer-facing chat that answers "what's open near me" style questions, or any tool needing current information beyond a model's training data.

Source README

Brave Search MCP Server

An MCP server implementation that integrates the Brave Search API, providing both web and local search capabilities.

Features

  • Web Search: General queries, news, articles, 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 when no results are found

Tools

  • brave_web_search

    • Execute web searches with pagination and filtering
    • Inputs:
      • query (string): Search terms
      • count (number, optional): Results per page (max 20)
      • offset (number, optional): Pagination offset (max 9)
  • brave_local_search

    • Search for local businesses and services
    • Inputs:
      • query (string): Local search terms
      • count (number, optional): Number of results (max 20)
    • Automatically falls back to web search if no local results found

Configuration

Getting an 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

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

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"
      }
    }
  }
}

NPX

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

Usage with VS Code

For quick installation, use the one-click installation buttons below...

Install with NPX in VS Code Install with NPX in VS Code Insiders

Install with Docker in VS Code Install with Docker in VS Code Insiders

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

Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.

Note that the mcp key is not needed in the .vscode/mcp.json file.

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

Build

Docker build:

docker build -t mcp/brave-search:latest -f src/brave-search/Dockerfile .

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.