# tiny-browse | AI tooling by Shubham Prakash

> An MCP server and Node library that gives any AI agent web search. It uses the Chrome you already have and returns clean Markdown inside a hard token budget.

Page: https://shubhamcodess.github.io/builds/tiny-browse/

## tiny-browse

An MCP server and Node library that gives any AI agent web search. It uses the Chrome you already have and returns clean Markdown inside a hard token budget.

- Page: https://shubhamcodess.github.io/builds/tiny-browse/
- Kind: AI tooling, 2026
- Stack: TypeScript, MCP, Chrome DevTools Protocol
- code: https://github.com/shubhamcodess/tiny-browse
- live: https://shubhamcodess.github.io/tiny-browse/
- package: https://www.npmjs.com/package/@shubhamcodess/tiny-browse

### Overview

A small MCP server and Node library that searches the web in **the Chrome you already have**, reads the best results and returns clean Markdown inside a **hard token budget**. There is no bundled browser, no API key and no LLM inside.

Measured:

- 0: runtime dependencies
- 126 kB: package size
- 2: tools: web_search and web_fetch

### What it does

- Works with any MCP client over stdio or a shared HTTP server, or as a dependency in code.
- Extracts the main content by page layout, keeping headings, code, tables and lists, and dropping menus, ads and cookie banners.
- Packs sections into the token budget, keeping the ones most relevant to the query.
- Powers the web lookup step in whatcmd.

### How it is built

- Search results are read three independent ways (layout, accessibility tree and selectors) and merged by vote, so a redesign rarely breaks it.
- Rate budgets per search engine are shared across every process on the machine, with longer pauses after a CAPTCHA.
- Bot checks are reported as blocked and never bypassed.
- No private-network access, and pages are read without your cookies.

### Honest limits

- Search engines may block automated browsers.
- No PDFs yet, and Windows is untested.

By Shubham Prakash: https://shubhamcodess.github.io/
