Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
npm install @brave/brave-search-mcp-serverAn MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, image search, video search, news search, and AI-powered summarization. This project supports both STDIO and HTTP transports, with STDIO as the default mode.

#### Default transport now STDIO
To follow established MCP conventions, the server now defaults to STDIO. If you would like to continue using HTTP, you will need to set the BRAVE_MCP_TRANSPORT environment variable to http, or provide the runtime argument --transport http when launching the server.
#### Response structure of brave_image_search
Version 1.x of the MCP server would return base64-encoded image data along with image URLs. This dramatically slowed down the response, as well as consumed unnecessarily context in the session. Version 2.x removes the base64-encoded data, and returns a response object that more closely reflects the original Brave Search API response. The updated output schema is defined in src/tools/images/schemas/output.ts.
Parameters:
- query (string, required): Search terms (max 400 chars, 50 words)
- country (string, optional): Country code (default: "US")
- search_lang (string, optional): Search language (default: "en")
- ui_lang (string, optional): UI language (default: "en-US")
- count (number, optional): Results per page (1-20, default: 10)
- offset (number, optional): Pagination offset (max 9, default: 0)
- safesearch (string, optional): Content filtering ("off", "moderate", "strict", default: "moderate")
- freshness (string, optional): Time filter ("pd", "pw", "pm", "py", or date range)
- text_decorations (boolean, optional): Include highlighting markers (default: true)
- spellcheck (boolean, optional): Enable spell checking (default: true)
- result_filter (array, optional): Filter result types (default: ["web", "query"])
- goggles (array, optional): Custom re-ranking definitions
- units (string, optional): Measurement units ("metric" or "imperial")
- extra_snippets (boolean, optional): Get additional excerpts (Pro plans only)
- summary (boolean, optional): Enable summary key generation for AI summarization
Parameters:
- Same as brave_web_search with automatic location filtering
- Automatically includes "web" and "locations" in result_filter
Note: Requires Pro plan for full local search capabilities. Falls back to web search otherwise.
Parameters:
- query (string, required): Search terms (max 400 chars, 50 words)
- country (string, optional): Country code (default: "US")
- search_lang (string, optional): Search language (default: "en")
- ui_lang (string, optional): UI language (default: "en-US")
- count (number, optional): Results per page (1-50, default: 20)
- offset (number, optional): Pagination offset (max 9, default: 0)
- spellcheck (boolean, optional): Enable spell checking (default: true)
- safesearch (string, optional): Content filtering ("off", "moderate", "strict", default: "moderate")
- freshness (string, optional): Time filter ("pd", "pw", "pm", "py", or date range)
Parameters:
- query (string, required): Search terms (max 400 chars, 50 words)
- country (string, optional): Country code (default: "US")
- search_lang (string, optional): Search language (default: "en")
- count (number, optional): Results per page (1-200, default: 50)
- safesearch (string, optional): Content filtering ("off", "strict", default: "strict")
- spellcheck (boolean, optional): Enable spell checking (default: true)
Parameters:
- query (string, required): Search terms (max 400 chars, 50 words)
- country (string, optional): Country code (default: "US")
- search_lang (string, optional): Search language (default: "en")
- ui_lang (string, optional): UI language (default: "en-US")
- count (number, optional): Results per page (1-50, default: 20)
- offset (number, optional): Pagination offset (max 9, default: 0)
- spellcheck (boolean, optional): Enable spell checking (default: true)
- safesearch (string, optional): Content filtering ("off", "moderate", "strict", default: "moderate")
- freshness (string, optional): Time filter (default: "pd" for last 24 hours)
- extra_snippets (boolean, optional): Get additional excerpts (Pro plans only)
- goggles (array, optional): Custom re-ranking definitions
Parameters:
- key (string, required): Summary key from web search results (use summary: true in web search)
- entity_info (boolean, optional): Include entity information (default: false)
- inline_references (boolean, optional): Add source URL references (default: false)
Usage: First perform a web search with summary: true, then use the returned summary key with this tool.
1. Sign up for a Brave Search API account
2. Choose a plan:
- Free: 2,000 queries/month, basic web search
- Pro: Enhanced features including local search, AI summaries, extra snippets
3. Generate your API key from the developer dashboard
The server supports the following environment variables:
- BRAVE_API_KEY: Your Brave Search API key (required)
- BRAVE_MCP_TRANSPORT: Transport mode ("http" or "stdio", default: "stdio")
- BRAVE_MCP_PORT: HTTP server port (default: 8000)
- BRAVE_MCP_HOST: HTTP server host (default: "0.0.0.0")
- BRAVE_MCP_LOG_LEVEL: Desired logging level("debug", "info", "notice", "warning", "error", "critical", "alert", or "emergency", default: "info")
- BRAVE_MCP_ENABLED_TOOLS: When used, specifies a whitelist for supported tools
- BRAVE_MCP_DISABLED_TOOLS: When used, specifies a blacklist for supported tools
- BRAVE_MCP_STATELESS: HTTP stateless mode (default: "true"). When running on Amazon Bedrock Agentcore, set to "true".
``bash
node dist/index.js [options]
Options:
--brave-api-key
--transport
--port
--host
--logging-level
--enabled-tools Tools whitelist (only the specified tools will be enabled)
--disabled-tools Tools blacklist (included tools will be disabled)
--stateless
`
To install Brave Search automatically via Smithery:
`bash`
npx -y @smithery/cli install brave
Add this to your claude_desktop_config.json:
#### Docker
`json`
{
"mcpServers": {
"brave-search": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "BRAVE_API_KEY", "docker.io/mcp/brave-search"],
"env": {
"BRAVE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
#### NPX
`json`
{
"mcpServers": {
"brave-search": {
"command": "npx",
"args": ["-y", "@brave/brave-search-mcp-server", "--transport", "http"],
"env": {
"BRAVE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
For quick installation, use the one-click installation buttons below:
 
 
For manual installation, add the following to your User Settings (JSON) or .vscode/mcp.json:
#### Docker
`json`
{
"inputs": [
{
"password": true,
"id": "brave-api-key",
"type": "promptString",
"description": "Brave Search API Key",
}
],
"servers": {
"brave-search": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "BRAVE_API_KEY", "mcp/brave-search"],
"env": {
"BRAVE_API_KEY": "${input:brave-api-key}"
}
}
}
}
#### NPX
`json`
{
"inputs": [
{
"password": true,
"id": "brave-api-key",
"type": "promptString",
"description": "Brave Search API Key",
}
],
"servers": {
"brave-search-mcp-server": {
"command": "npx",
"args": ["-y", "@brave/brave-search-mcp-server", "--transport", "stdio"],
"env": {
"BRAVE_API_KEY": "${input:brave-api-key}"
}
}
}
}
`bash`
docker build -t mcp/brave-search:latest .
`bash`
npm install
npm run build
- Node.js 22.x or higher
- npm
- Brave Search API key
1. Clone the repository:
`bash`
git clone https://github.com/brave/brave-search-mcp-server.git
cd brave-search-mcp-server
2. Install dependencies:
`bash`
npm install
3. Build the project:
`bash`
npm run build
Add a reference to your local build in claude_desktop_config.json:
`json`
{
"mcpServers": {
"brave-search-dev": {
"command": "node",
"args": ["C:\\GitHub\\brave-search-mcp-server\\dist\\index.js"], // Verify your path
"env": {
"BRAVE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
1. Build and start the server:
`bash`
npm run build
node dist/index.js
2. In another terminal, start the MCP Inspector:
`bash`
npx @modelcontextprotocol/inspector node dist/index.js
STDIO is the default mode. For HTTP mode testing, add --transport http to the arguments in the Inspector UI.
1. Establish and acquire a smithery.ai account and API key
2. Run npm run install, npm run smithery:build, and lastly npm run smithery:dev to begin testing
- npm run build: Build the TypeScript projectnpm run watch
- : Watch for changes and rebuildnpm run format
- : Format code with Prettiernpm run format:check
- : Check code formattingnpm run prepare
- : Format and build (runs automatically on npm install)
- npm run inspector: Launch an instance of MCP Inspectornpm run inspector:stdio
- : Launch a instance of MCP Inspector, configured for STDIOnpm run smithery:build
- : Build the project for smithery.ainpm run smithery:dev
- : Launch the development environment for smithery.ai
For local development with Docker:
`bash``
docker-compose up --build
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.