An MCP server for Nullprint, the multi-profile browser. It lets any MCP-capable AI agent (Claude Code, Claude Desktop, OpenAI Codex, Kimi, …) create browser profiles, launch them, run consistency…
Nullprint is an MCP project maintained in the nullprintai/nullprint-mcp repository. The maintainer describes its purpose as “An MCP server for Nullprint, the multi-profile browser. It lets any MCP-capable AI agent (Claude Code, Claude Desktop, OpenAI Codex, Kimi, …) create browser profiles…”. Read the project documentation for the complete scope.
The documented pypi package is nullprint-mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-13.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| profiles_list | List every profile with status (running / idle), exit and ledger metadata |
| profile_start | Open a browser session for a profile; returns the driving endpoints |
| profile_stop | Stop that profile's browser (session or app-launched window) |
| profile_create | Create a profile (fingerprint generated and frozen), optionally with proxy, ledger and start pages |
| profile_checkup | Consistency check-up, returns {summary, checks} |
| proxy_check | Stateless proxy test: exit IP, country, latency |
| profile_delete | Soft delete to the recycle bin (recoverable); refused while running |
| trash_list | Read-only list of recoverable profiles in the recycle bin |
| profile_restore | Restore from the recycle bin with fingerprint, proxy and logins intact |
| session_goto | Navigate the session's current page |
| session_snapshot | Accessibility tree of the current page (find selectors, read state) |
| session_click_selector | Click an element by CSS selector |
| session_fill_selector | Fill an input by CSS selector |
| session_press | Send a key (e.g. Enter) |
| session_eval | Run JavaScript on the page, returns {ok, result} |
| session_tabs | List the session's tabs and the active one |
| session_switch_tab | Bring a tab to the front |
{
"mcpServers": {
"nullprint": {
"command": "uvx",
"args": [
"nullprint-mcp"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Edit video in your open VidTL browser editor: cuts, subtitles, audio cleanup, effects, export.
A universal Model Context Protocol (MCP) server for browser automation that works reliably in containerized environments with limited privileges. It provides browser control capabilities to AI…
Chromewright is a local-first browser automation MCP server built on Chrome DevTools Protocol (CDP). It exposes a real Chrome or Chromium browser to
A Model Context Protocol server that provides browser automation capabilities using Playwright and Deno 2.