mcp-server-agent-browser

Status: Beta — CLI wrapper is covered by unit tests and a fake-browser stdio smoke test. Cookie restore across a real Chromium restart is still a manual check.

Let LLMs drive a real browser. This MCP server wraps agent-browser (Vercel Labs) so any MCP client can navigate, fill forms, click, snapshot the accessibility tree, and screenshot.

It is not Grok's web_search / open_page. Those fetch documents. This one runs Chromium. Use search to find a URL, then browser_navigate.

Prerequisites

cargo install agent-browser
agent-browser install

Call browser_doctor if anything is missing.

Build

cargo build --release

Binary: target/release/mcp-server-agent-browser

cargo test
./tests/test-stdio.sh

Real Chromium login-restore is not in CI. After a headed login, restart the MCP process and confirm the next browser_navigate is still logged in.

Configuration

MCP client (stdio):

{
  "mcpServers": {
    "agent-browser": {
      "command": "/path/to/mcp-server-agent-browser"
    }
  }
}

Optional TOML at ~/.config/mcp-server-agent-browser/config.toml (see config.example.toml). Missing file uses defaults. Override the path with MCP_AGENT_BROWSER_CONFIG.

Setting	Default	Meaning
`headed`	`false`	Show a window. Launch-time only; `browser_close` first if a headless daemon is already up. Also `AGENT_BROWSER_HEADED=1`.
`persist`	`true`	Bare `--restore` per `session_id` (default session key `default`) plus `--namespace mcp-server`.
`keep_daemon`	`false`	If false, MCP exit runs `close` so restore state is saved and Chrome does not leak.
`namespace`	`mcp-server`	Isolates this MCP's daemon sockets and restore files from a human using the CLI.
`command_timeout_secs`	`120`	Wrapper timeout. Playwright's own 25s action timeout is left alone (CLI IPC is ~30s).
`idle_timeout`	`1h`	Daemon idle shutdown. Use `"0"` with `keep_daemon = true`.
`download_dir`	`~/Downloads`	`--download-path`. `~` is expanded.
`profile`	unset	Optional persistent Chrome user-data dir. Not your daily Chrome profile.
`encryption_key_file`	unset	Sets `AGENT_BROWSER_ENCRYPTION_KEY`. Restore files are credentials; plaintext unless this is set.
`AGENT_BROWSER_PATH`	`agent-browser`	CLI binary.

allowed_domains is optional. Localhost is allowed unless you set a list that excludes it.

What it can do

Same interaction set as before (navigate, click, type, snapshot, screenshot, cookies, eval, CDP, sessions), plus:

browser_doctor — CLI, config, persist, headed/DISPLAY, daemon guess. Does not launch Chrome.
browser_get_text pattern — regex over page text with two lines of context.
browser_wait — load / url / text as well as a selector.

Typical loop:

browser_navigate
browser_snapshot (-i for interactive)
browser_click / browser_fill with @refs
browser_screenshot if you need pixels

Persistence

With persist = true (default), each session saves cookies and localStorage on close and on the CLI's autosave interval. State lives under ~/.agent-browser/, namespaced to mcp-server. Isolated session_ids do not share a restore key.

Headed login once, browser_close or exit the MCP, start again. The next navigate should restore that session.

A killed MCP process may leave the daemon running. browser_doctor reports that. Idle shutdown still saves if persist is on.

Limitations

Chromium via agent-browser (Playwright). No search.
Headed is ignored until the existing daemon is closed.
Snap Chromium on Ubuntu can fail to advertise its DevTools port; prefer agent-browser install's browser or executable_path.
Writes (screenshot, pdf, download) must be relative, under /tmp, or under download_dir.
25s Playwright action timeout is an upstream CLI limit, not this wrapper.

License

MIT

mcp server agent browser