The Brave Search MCP Server integrates with the Brave Search API to provide various search capabilities:
Web Search: Perform general searches across diverse web sources (maximum 20 results per request)
Image Search: Find web images based on specific queries (maximum 3 results per request)
News Search: Retrieve news articles and trending topics (maximum 20 results per request)
Video Search: Search for video content and tutorials (maximum 20 results per request)
Local Search: Find businesses, restaurants, and points of interest nearby (maximum 20 results per request, falls back to web search if no local results are found)
Provides Web Search, Local Points of Interest Search, Video Search, Image Search and News Search capabilities through the Brave Search API, allowing users to retrieve various types of search results.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Brave Search MCPfind recent news about AI advancements"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Brave Search MCP Server
An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Video Search, Image Search and News Search capabilities
Features
Web Search: Perform a regular search on the web
Image Search: Search the web for images.
News Search: Search the web for news
Video Search: Search the web for videos
Local Points of Interest Search: Search for local physical locations, businesses, restaurants, services, etc
Related MCP server: Brave Search MCP Server
Tools
brave_web_search
Execute web searches using Brave's API
Inputs:
query(string): The term to search the internet forcount(number, optional): The number of results to return (max 20, default 10)offset(number, optional, default 0): The offset for paginationfreshness(enum, optional): Filters search results by when they were discoveredThe following values are supported
pd: Discovered within the last 24 hours.
pw: Discovered within the last 7 Days.
pm: Discovered within the last 31 Days.
py: Discovered within the last 365 Days
YYYY-MM-DDtoYYYY-MM-DD: Custom date range (e.g., 2022-04-01to2022-07-30)
brave_image_search
Get images from the web relevant to the query
Inputs:
query(string): The term to search the internet for images ofcount(number, optional): The number of images to return (max 50, default 10)
brave_news_search
Searches the web for news
Inputs:
query(string): The term to search the internet for news articles, trending topics, or recent eventscount(number, optional): The number of results to return (max 20, default 10)offset(number, optional, default 0): The zero-based offset for pagination (max 9)freshness(enum, optional): Filters search results by when they were discoveredThe following values are supported
pd: Discovered within the last 24 hours.
pw: Discovered within the last 7 Days.
pm: Discovered within the last 31 Days.
py: Discovered within the last 365 Days
YYYY-MM-DDtoYYYY-MM-DD: Custom date range (e.g., 2022-04-01to2022-07-30)
brave_local_search
Search for local businesses, services and points of interest
REQUIRES subscription to the Pro api plan for location results
Falls back to brave_web_search if no location results are found
Inputs:
query(string): Local search termcount(number, optional): The number of results to return (max 20, default 5)offset(number, optional, default 0): The zero-based offset for pagination (max 9)
brave_video_search
Search the web for videos
Inputs:
query: (string): The term to search for videoscount: (number, optional): The number of videos to return (max 20, default 10)offset(number, optional, default 0): The zero-based offset for pagination (max 9)freshness(enum, optional): Filters search results by when they were discoveredThe following values are supported
pd: Discovered within the last 24 hours.
pw: Discovered within the last 7 Days.
pm: Discovered within the last 31 Days.
py: Discovered within the last 365 Days
YYYY-MM-DDtoYYYY-MM-DD: Custom date range (e.g., 2022-04-01to2022-07-30)
OpenAI Apps & MCP Apps Support
There is now support for OpenAI Apps and MCP Apps in this MCP Server. When UI mode is enabled for each tool there is a corresponding UI widget that let's you control what gets added to the model's context. See the directions in usage with ChatGPT section.
Configuration
Getting an API Key
Sign up for a Brave Search API account
Choose a plan (Free tier available with 2,000 queries/month)
Generate your API key from the developer dashboard
Streamable HTTP mode
By default the MCP server runs in stdio mode.
To enable Streamable HTTP mode:
By default the server listens on port 3001. The URL is:
Environment variables
When running in HTTP mode, the following environment variables are supported:
BRAVE_API_KEY(required): Brave Search API key.PORT(optional): HTTP port (default:3001).HOST(optional): Interface to bind to (default:0.0.0.0).ALLOWED_HOSTS(optional): Comma-separated list of allowed hostnames for Host header validation.Example:
ALLOWED_HOSTS=localhost,127.0.0.1,my-app.ngrok-free.appUse hostnames only (no scheme/path), e.g.
my-app.ngrok-free.appnothttps://my-app.ngrok-free.app/mcp
Examples:
Usage with ChatGPT
The Brave Search MCP Server can be used with the web UI of ChatGPT. It takes a few steps.
1. Enable Developer Mode in ChatGPT
Settings → Apps → Advanced settings → Developer mode
Additional instructions here
2. Run the Brave Search MCP in HTTP mode and UI mode
3. Create a local tunnel to expose the MCP Server to ChatGPT
Sign up and configure ngrok, the free plan works.
Take note of the forwarding URL.
4. Add Brave Search MCP as a Connector to ChatGPT
Click Apps
Click Create Apps
Fill out the form using the URL from step 3 as the MCP Server URL, but add /mcp.
For Authentication, select 'No Auth'
Tick the checkbox for 'I understand and want to continue'
Then click Create.
5. Using the Brave Search MCP Server
In the ChatGPT UI, click the '+' button, scroll to '...more', select the newly created Brave Search app, and enter your query.
Usage with Claude Code
For Claude Code users, run this command:
Windows:
Linux/macOS:
Replace YOUR_API_KEY_HERE with your actual Brave Search API key.
Usage with Claude Desktop
MCP Bundle (MCPB)
Download the
mcpbfile from the ReleasesOpen it with Claude Desktop or Go to File -> Settings -> Extensions and drag the .mcpb file to the window to install it
Docker
Clone the repo
Docker build
Add this to your
claude_desktop_config.json:
NPX
Add this to your claude_desktop_config.json:
Usage with LibreChat
Add this to librechat.yaml
Contributing
Contributions are welcome! See CONTRIBUTING.md for development setup, monorepo structure, and release instructions.
Disclaimer
This library is not officially associated with Brave Software. It is a third-party implementation of the Brave Search API with a MCP Server.
License
This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.