Connect the Brave Search MCP for Real-Time Web Research
Claude's training data has a cutoff — but with the Brave Search MCP server connected, it can look things up in real time before answering.
Add it to your Claude Code config with a free Brave Search API key:
{
"mcpServers": {
"brave-search": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-brave-search"],
"env": {
"BRAVE_API_KEY": "your-api-key-here"
}
}
}
}
Once connected, Claude can search the web mid-conversation without you having to leave the terminal:
What's the latest stable version of Bun, and has anything
changed in the HTTP server API since 1.0?
This is especially useful when working with fast-moving ecosystems — framework changelogs, new library APIs, recent CVEs, or package deprecation notices. Claude will search, read the relevant pages, and synthesise an answer grounded in current docs rather than memory.
You can get a free Brave Search API key at brave.com/search/api — the free tier covers 2,000 queries per month.
Stop copy-pasting docs into the chat — let Claude search for what it needs.
Log in to leave a comment.
MCP servers aren't just for third-party integrations — you can build your own to give Claude direct access to your internal tools, databases, APIs, and workflows. A custom MCP server turns any system your team uses into a tool Claude can call natively from your session.
MCP servers can be scoped at three levels — user (available everywhere you work), project (shared with the team via version control), or enterprise (managed by your organization). Pick the right scope so each project gets exactly the tools it needs without cluttering unrelated ones.
Instead of manually editing settings JSON to add MCP servers, use the claude mcp command — add servers with one line, list what's configured, remove ones you don't need, and scope them to the right level, all from the terminal.