Skip to main content

Web search

Web search. In the CLI, over MCP, however you work.

Search the live web and get back text, not a page of links. Connected once, it answers the terminal and every AI you already use, under one permission.

Results come back as title, url, date and the readable text of the page, which is what an agent needs and what a person reading a terminal wants too. Searches cost money, so they are the clearest thing a daily limit stops.

A real command line for web search

Not a chat window pretending. Every argument is a flag, output is text a pipe can read, and each call lands on the record with the daily ceiling watching.

Connect the account once, in the browser, and the terminal has it from then on. No key on the laptop, nothing in the shell history worth stealing.

Web search from the command line

Or hand Web search to the AI you already use

Claude Code, Cursor and Codex all speak MCP. Point any of them at one endpoint and they get the same web search tools, on the same permission and the same record as the terminal.

Web search over MCP, tool by tool

claude mcp add gbrain --transport http https://gbrain.io/mcp

The AI gets exa_search. Run /mcp in Claude Code and choose Authenticate, and GBrain asks what it may reach.