Brave Search MCP: Complete Setup and Usage Guide 2026

Add real-time web search to your AI applications - step-by-step guide to Brave Search MCP

返回教程列表
进阶15 分钟

Brave Search MCP: Complete Setup and Usage Guide 2026

Add real-time web search to your AI applications - step-by-step guide to Brave Search MCP

Brave Search MCP: Complete Guide 2026 What is Brave Search MCP? **Brave Search MCP** is an MCP (Model Context Protocol) server that enables AI assistants to Add real-time web search to your AI applications. MCP is an open protocol that standardizes

Brave Search MCP: Complete Guide 2026

What is Brave Search MCP?

Brave Search MCP is an MCP (Model Context Protocol) server that enables AI assistants to Add real-time web search to your AI applications. MCP is an open protocol that standardizes how AI models interact with external tools and data sources.

Prerequisites

  • Claude Desktop (or any MCP-compatible client)
  • Node.js 18+ or Python 3.10+
  • Access to Brave account/credentials
  • Installation

    Option 1: NPM (Recommended)

    bash
    npm install -g @search/brave-search-mcp-mcp
    

    Option 2: From Source

    bash
    git clone https://github.com/modelcontextprotocol/brave-search-mcp-mcp
    cd brave-search-mcp-mcp
    npm install
    npm run build
    

    Configuration

    Claude Desktop Setup

    Edit your Claude Desktop config file:

    macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

    json
    {
      "mcpServers": {
        "brave-search-mcp": {
          "command": "npx",
          "args": [
            "-y",
            "@search/brave-search-mcp-mcp"
          ],
          "env": {
            "BRAVE_SEARCH_MCP_API_KEY": "your-api-key-here",
            "DEBUG": "false"
          }
        }
      }
    }
    

    Environment Variables

    bash
    

    Required

    export BRAVE_SEARCH_MCP_API_KEY=your_key_here

    Optional

    export BRAVE_SEARCH_MCP_TIMEOUT=30 export BRAVE_SEARCH_MCP_MAX_RESULTS=50

    Available Tools

    After installation, Claude has access to these tools:

    Core Tools

    
    
  • brave_search_mcp_list
  • Description: List available resources Parameters: { limit: number, filter: string }

  • brave_search_mcp_get
  • Description: Get specific resource by ID or name Parameters: { id: string }

  • brave_search_mcp_create
  • Description: Create a new resource Parameters: { name: string, content: any }

  • brave_search_mcp_update
  • Description: Update existing resource Parameters: { id: string, updates: any }

  • brave_search_mcp_delete
  • Description: Delete a resource Parameters: { id: string, confirm: boolean }

    Usage Examples

    Example 1: Basic Usage in Claude

    Once configured, you can ask Claude naturally:

    
    You: "Use Brave Search MCP to help me with Add real-time web search to your AI applications"

    Claude: "I'll use the Brave Search MCP MCP server to help you. [Uses brave_search_mcp_list tool] Here's what I found..."

    Example 2: Complex Workflow

    
    You: "Please analyze my search setup and suggest improvements"

    Claude will:

  • List all resources using Brave Search MCP
  • Analyze the current configuration
  • Identify opportunities for improvement
  • Suggest specific changes with reasoning
  • Building a Custom MCP Server

    You can also build your own MCP server:

    typescript
    import { Server } from "@modelcontextprotocol/sdk/server/index.js";
    import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
    import {
      CallToolRequestSchema,
      ListToolsRequestSchema,
    } from "@modelcontextprotocol/sdk/types.js";

    const server = new Server( { name: "my-search-server", version: "0.1.0", }, { capabilities: { tools: {}, }, } );

    // Define available tools server.setRequestHandler(ListToolsRequestSchema, async () => { return { tools: [ { name: "search_query", description: "Add real-time web search to your AI applications", inputSchema: { type: "object", properties: { query: { type: "string", description: "Your query" } }, required: ["query"] } } ] }; });

    // Handle tool calls server.setRequestHandler(CallToolRequestSchema, async (request) => { if (request.params.name === "search_query") { const { query } = request.params.arguments as { query: string }; // Your implementation here const result = await performQuery(query); return { content: [ { type: "text", text: JSON.stringify(result, null, 2) } ] }; } throw new Error(Unknown tool: ${request.params.name}); });

    // Start server const transport = new StdioServerTransport(); await server.connect(transport);

    Troubleshooting

    Common Issues

    Issue: Server not starting

    bash
    

    Check if node is properly installed

    node --version # Should be 18+

    Reinstall the package

    npm install -g @search/brave-search-mcp-mcp --force

    Issue: Authentication failing

    bash
    

    Verify your API key

    echo $BRAVE_SEARCH_MCP_API_KEY

    Test API key validity

    curl -H "Authorization: Bearer $BRAVE_SEARCH_MCP_API_KEY" https://api.brave.com/v1/test

    Security Considerations

    bash
    

    Use environment-specific keys (never hardcode)

    In production, use a secrets manager

    export BRAVE_SEARCH_MCP_API_KEY=$(aws secretsmanager get-secret-value --secret-id mcp-keys --query SecretString --output text | jq -r '.search_key')

    Limit MCP server permissions to minimum required

    Use read-only tokens when possible

    Conclusion

    Brave Search MCP unlocks the ability to Add real-time web search to your AI applications directly through your AI assistant. This makes complex search tasks dramatically faster and more intuitive.


    *Brave Search MCP MCP setup guide | May 2026*

    相关工具

    Claude DesktopMCPBrave Search MCP