I gave my coding agent eyes on my real, logged-in browser (stdlib-only, local)

A developer built browser-buddy, an MIT-licensed MCP server plus Chrome Manifest V3 extension that lets coding agents read pages through the user's real, logged-in Chrome profile, including cookies and sessions, to bypass 403s, login walls and bot detection. The tool uses a stdio MCP server, a Unix-socket native host and chrome.runtime.connectNative, exposes two tools (read_active_tab and open_and_read_url), passes 17/17 smoke tests, and is published on the official MCP registry as io.github.hahahahahahahahah6/browser-buddy. Everything runs locally with zero dependencies, and the developer says next steps are real-world testing on Windows Chrome.

Every agentic coding tool hits the same wall eventually: the page you need is behind a login, a 403, or bot detection, and the agent's server-side fetcher is locked out. Your browser is logged in. Your agent is not. So the fix is not a better scraper — it is letting the agent borrow your eyes . I built browser-buddy https://github.com/hahahahahahahahah6/browser-buddy , an MCP server + Chrome extension Manifest V3 that lets coding agents read pages through the user's real Chrome profile: cookies, sessions, logins included. MIT licensed, zero dependencies, nothing leaves your machine. Three pieces, each dumb and replaceable: chrome.runtime.connectNative on one side, a socket server on the other. mcp SDK package; the protocol surface I need is two tools, so I hand-rolled the framing in ~200 lines: TOOLS = { "name": "read active tab", "description": "Read the user's currently active Chrome tab through their real, " "logged-in browser profile. Returns the page URL, title, and " "cleaned readable text. Use when WebFetch/fetch is blocked by a " "403, login wall, or bot detection." , "inputSchema": {"type": "object", "properties": {}, "additionalProperties": False}, }, { "name": "open and read url", "description": "Open a URL in a background Chrome tab using the user's real " "browser profile cookies and login sessions included , extract " "its readable text, then close the tab." , ... }, Message flow for open and read url : agent ──JSON-RPC/stdio──▶ MCP server ──Unix socket──▶ native host │ connectNative ▼ Chrome extension ──▶ tab Logs go to stderr stdout is reserved for protocol messages — the classic stdio footgun, handled once and never again . Headless browsers are new browsers: no cookies, no sessions, and they get fingerprinted as bots — the exact problem I was trying to escape. The insight is embarrassingly simple: the most authenticated, least-bot-detected browser in existence is the one the user is already using. So don't automate a fake browser; ask the real one to read. This design is only acceptable because everything is local: 17/17 smoke tests pass framing, tool schemas, socket relay, tab extraction mocks , and it's live on the official MCP registry as io.github.hahahahahahahahah6/browser-buddy . Next: real-world testing on Windows Chrome. Try it: uvx browser-buddy-mcp needs the extension + host from the repo . Built in the open. Issues and PRs welcome — especially from people whose agents keep getting 403'd.