Brave-Search-MCP-SSE
Documentation
Brave Search MCP with SSE Support
This is a Model Context Protocol (MCP) server that provides Brave Search capabilities with Server-Sent Events (SSE) integration. It can be deployed to Coolify and used as a real-time search service.
Features
- Brave Search API integration through MCP
- Real-time search results using SSE
- Docker and Coolify ready
- TypeScript implementation
- Express.js SSE endpoint
Prerequisites
- Brave Search API key
- Node.js 18+
- Docker (for containerized deployment)
- Coolify instance
Local Development
1. Clone the repository
2. Create a `.env` file with your Brave API key:
BRAVE_API_KEY=your_api_key_here
PORT=30013. Install dependencies:
npm install4. Start development server:
npm run devDocker Deployment
1. Build and run using docker-compose:
docker-compose up --buildCoolify Deployment
1. In your Coolify dashboard, create a new service
2. Choose "Deploy from Source"
3. Configure the following:
Using the SSE Integration
SSE Endpoint
GET http://your-server:3001/sseThe SSE endpoint provides real-time search results. Connect to it using the EventSource API:
const eventSource = new EventSource('http://your-server:3001/sse');
eventSource.onmessage = (event) => {
const data = JSON.parse(event.data);
// Handle the search results
console.log(data);
};
eventSource.onerror = (error) => {
console.error('SSE Error:', error);
eventSource.close();
};Messages Endpoint
POST http://your-server:3001/messages
Content-Type: application/json
{
"query": "your search query",
"count": 10 // optional, default: 10, max: 20
}Use this endpoint to trigger searches that will be broadcast to all connected SSE clients.
MCP Usage
The server provides the following MCP tool:
- `brave_web_search`: Performs a web search using the Brave Search API
{
query: string; // Search query
count?: number; // Number of results (1-20, default: 10)
}Error Handling
- The server broadcasts errors to all connected SSE clients
- Errors are formatted as:
{
"type": "error",
"error": "error message"
}Notes
- The SSE connection will stay open until the client closes it
- Each search result is broadcast to all connected clients
- The server automatically handles disconnections and cleanup
- For production deployment, consider implementing authentication for the messages endpoint
Frequently asked questions
What is Brave-Search-MCP-SSE?
Brave-Search-MCP-SSE is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install Brave-Search-MCP-SSE?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is Brave-Search-MCP-SSE open source?
Yes — it is hosted on GitHub at https://github.com/isaacgounton/brave-search-mcp-sse.
Related MCP tools
Model Context Protocol Servers
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Built for the Model Context Protocol to enhance AI capabilities.
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini...
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, ...
Composio equips your AI agents & LLMs with 100+ high-quality integrations via function calling for the Model Context Protocol. Enhance AI assistants with powerf
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP