Skip to main content
Glama
cuer-bot

Brave Search MCP Server

by cuer-bot

Brave Search MCP Server

An MCP (Model Context Protocol) server that provides web search via Brave Search API. Designed for Claude Code and Claude Desktop integration.

Features:

  • Web search with freshness filters (past day/week/month/year)

  • Full page content fetching with markdown extraction

  • AI-optimized result metadata (authority, content type, recency)

  • Usage tracking with monthly limits (2,000 free requests)

Prerequisites

  • Node.js 18+

  • Brave Search API key (free tier)

Related MCP server: Brave Search MCP Server

Getting a Brave API Key

  1. Go to https://brave.com/search/api/

  2. Click "Get Started" or "Get API Key"

  3. Create an account or sign in

  4. Navigate to API keys section

  5. Generate a new API key

  6. Copy the key (you won't see it again)

Note: Free tier includes 2,000 requests/month with no rate limiting.

Installation

git clone <repo-url>
cd bravesearchmcp
npm install
cp .env.example .env
# Edit .env and add your BRAVE_API_KEY

Claude Desktop Configuration

macOS

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "brave-search": {
      "command": "npx",
      "args": ["tsx", "/absolute/path/to/bravesearchmcp/src/index.ts"],
      "env": {
        "BRAVE_API_KEY": "your_api_key_here"
      }
    }
  }
}

Windows

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "brave-search": {
      "command": "npx",
      "args": ["tsx", "C:\\path\\to\\bravesearchmcp\\src\\index.ts"],
      "env": {
        "BRAVE_API_KEY": "your_api_key_here"
      }
    }
  }
}

Claude Code Configuration

Add to your Claude Code MCP settings:

{
  "brave-search": {
    "command": "npx",
    "args": ["tsx", "/path/to/bravesearchmcp/src/index.ts"],
    "env": {
      "BRAVE_API_KEY": "your_api_key_here"
    }
  }
}

Available Tools

Tool

Description

brave_web_search

Search the web with optional freshness filter and result count

brave_fetch_page

Fetch and extract content from a URL as markdown

Usage Examples

Search:

Use brave_web_search to find recent articles about TypeScript 5.4 features

Fetch page:

Use brave_fetch_page to get the content from https://example.com/article

Usage Tracking

The server tracks your monthly API usage:

  • Displayed with each search result: "Usage: X/2000 (Y%)"

  • Warning at 80%: "Warning: approaching limit"

  • Warning at 95%: "Critical: nearly exhausted"

  • Counter resets on the 1st of each month

  • Usage stored in .brave-usage.json (gitignored)

Troubleshooting

Issue

Solution

"BRAVE_API_KEY environment variable is required"

Set the API key in Claude Desktop config or .env file

"Invalid API key"

Check your key at brave.com/search/api dashboard

"Rate limit exceeded"

Wait a moment - Brave has burst protection

Server not appearing in Claude

Restart Claude Desktop after config changes

License

MIT

A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cuer-bot/bravesearchmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server