Brave Search

v1.0.0Search & Data Extractionstable

An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Image Search, Video Search, News Search and LLM Context Search capabilities

brave-searchimage-searchmcpmcp-appsmodel-context-protocol
Share:
117
Stars
0
Downloads
0
Weekly
0/5

What is Brave Search?

Brave Search is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server implementation that integrates the brave search api, providing, web search, local points of interest search, image search, video search, news search and llm context search capabilities

An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Image Search, Video Search, News Search and LLM Context Search capabilities

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP Server implementation that integrates the Brave Searc

Use Cases

Perform web searches, image searches, and video searches via Brave API.
Execute news search and LLM context search with high-quality results.
Access multiple search modalities including local points of interest discovery.
mikechao

Maintainer

LicenseGPL 3.0
Languagetypescript
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx brave-search-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Brave Search

Brave Search MCP is an MCP server that wraps the Brave Search API and exposes six distinct search tools: web search, image search, video search, news search, local points-of-interest search, and an LLM-context search that returns pre-extracted content optimised for AI grounding and RAG pipelines. It is ideal for giving AI assistants real-time, privacy-respecting internet access without relying on Google or Bing. A single Brave Search API key is required, and the server supports optional rate-limiting, audit logging, and TOML-based policy configuration.

Prerequisites

  • Node.js 18+ and npx
  • A Brave Search API key — sign up at https://brave.com/search/api/ (free tier available)
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Obtain a Brave Search API key

Create an account at the Brave Search API developer portal and generate an API key. The free tier provides up to 2,000 queries per month.

# Visit https://brave.com/search/api/ to sign up and get your key
# The key looks like: BSA...
2

Test the server with npx

Run the server directly with npx to verify the API key works before configuring a permanent MCP integration.

BRAVE_API_KEY="your_key_here" npx -y brave-search-mcp
3

Add to Claude Desktop configuration

Edit your claude_desktop_config.json to register the Brave Search MCP server. The BRAVE_API_KEY environment variable is required.

# File location:
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%\Claude\claude_desktop_config.json
4

Optional: configure rate limits and audit logging

Create a TOML config file to limit request rates and enable audit logging. Point the server at the file via the BRAVE_MCP_CONFIG env var.

# config.toml
[guardrail]
requestLimit = 100
windowSeconds = 60
cooldownSeconds = 10

[audit]
enabled = true
logRaw = false

[server]
allowedHosts = ["localhost", "127.0.0.1"]
5

Restart Claude Desktop and verify tools

Restart the Claude Desktop app to load the new MCP server config. You should now have access to six Brave search tools in your AI assistant.

# Tools available after setup:
# brave_web_search, brave_image_search, brave_news_search,
# brave_local_search, brave_video_search, brave_llm_context_search

Brave Search Examples

Client configuration (Claude Desktop)

Full configuration block for claude_desktop_config.json with the required API key environment variable.

{
  "mcpServers": {
    "brave-search": {
      "command": "npx",
      "args": ["-y", "brave-search-mcp"],
      "env": {
        "BRAVE_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Prompts to try

Each prompt exercises a different Brave Search tool. The LLM context search is especially useful for grounding answers in recent web content.

- "Search the web for the latest developments in quantum computing."
- "Find recent news articles about the EU AI Act."
- "Search for images of the Aurora Borealis."
- "Find coffee shops near downtown Seattle."
- "Search for YouTube videos explaining how transformers work."
- "Use LLM context search to get grounding content about TypeScript 5.5 features."

Troubleshooting Brave Search

API key authentication errors or 401 responses

Double-check that BRAVE_API_KEY is set correctly in the env block of your MCP config. Keys from the Brave developer portal start with `BSA`. Ensure no extra whitespace or quotes surround the value.

Rate limit exceeded errors during heavy use

Create a TOML config file with a `[guardrail]` section and set `BRAVE_MCP_CONFIG` to its path. The free tier allows 2,000 requests/month, so consider upgrading your plan for production workloads.

`brave_local_search` returns no results

Local POI search requires a location query (e.g., 'coffee shops near Seattle'). The tool automatically falls back to web search when no local results are found, so vague queries may return web results instead.

Frequently Asked Questions about Brave Search

What is Brave Search?

Brave Search is a Model Context Protocol (MCP) server that mcp server implementation that integrates the brave search api, providing, web search, local points of interest search, image search, video search, news search and llm context search capabilities It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Brave Search?

Follow the installation instructions on the Brave Search GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Brave Search?

Brave Search works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Brave Search free to use?

Yes, Brave Search is open source and available under the GPL 3.0 license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "brave-search-mcp": { "command": "npx", "args": ["-y", "brave-search-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Brave Search?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides