The official Brave Search MCP server enables AI agents to perform web searches.
npx -y @modelcontextprotocol/server-brave-search
{
"mcpServers": {
"brave-search": {
"env": {
"BRAVE_API_KEY": "your-key"
},
"args": [
"-y",
"@modelcontextprotocol/server-brave-search"
],
"command": "npx"
}
}
}Search for local businesses and places
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string"
}
}
}// Input
{
"query": "coffee shops in Prague"
}// Output
{
"results": [
{
"name": "Kavarna",
"rating": 4.5,
"address": "Praha 1"
}
]
}Perform a web search using Brave Search API
{
"type": "object",
"required": [
"query"
],
"properties": {
"count": {
"type": "integer"
},
"query": {
"type": "string"
}
}
}// Input
{
"count": 5,
"query": "MCP servers"
}// Output
{
"results": [
{
"url": "https://github.com/modelcontextprotocol/servers",
"title": "MCP Servers"
}
]
}The official Brave Search MCP server enables AI agents to perform web searches.
Brave Search provides 2 tools including brave_local_search, brave_web_search.
Brave Search offers a free tier with 2000 calls per month. For higher usage, paid plans start at €0/month.
You can install Brave Search using the following command: npx -y @modelcontextprotocol/server-brave-search. After installation, add the provided config snippet to your Claude Desktop or Cursor configuration.
Brave Search is listed under the Data & Analytics category in the AgentForge MCP registry.
Brave Search has a current uptime of 99.95% with an average response time of 320ms.
To connect Brave Search, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of Brave Search's tools via the Model Context Protocol.