Screen Browser is an MCP server. An agent that knows your codebase already knows what every button is called, which makes it the best guide author you have.
Setup, once per machine
Register the server with your agent:
claude mcp add --transport http screenbrowser https://mcp.screenbrowser.com
The first time the agent uses a Screen Browser tool, your browser opens to sign in, pick the
organisation the agent may work in and approve, with no key to paste. If Claude Code does not
prompt, run /mcp and choose screenbrowser → Authenticate. Cursor and other MCP clients
that support OAuth add the same URL and sign in the same way. In Claude on the web or desktop, add
Screen Browser from the Claude directory. You can
disconnect an agent at any time under Settings → API keys → Connected agents.
If the agent cannot open a browser, use a key from Settings → API keys instead:
claude mcp add --transport http screenbrowser https://mcp.screenbrowser.com \
--header "Authorization: Bearer sb_live_…"
Then ask for what you want in plain words: "make a tutorial video of creating a campaign". The Claude Code guide shows one real session from that sentence to the finished video, with the exact prompt and what the agent did with it; the Codex guide shows the same request to OpenAI's Codex, which also reviewed its own takes frame by frame, and the Cursor guide the same request to Cursor's agent.
What the agent does
get_credits: is there balance?list_projects, orcreate_projectwith the deployed URL, the login gate read from the post-login redirect in the code, the hosts the frontend calls, and the demo user's credentials as variables.- Writes the auth guide from the login form and the main guide from the feature, in plain language, naming things as the templates label them.
validate_guideuntil it passes,put_guidefor both,start_run, thenget_runevery 15–30 seconds until the run is terminal.- Hands you the video link and the credits charged.
Tools
| Tool | Does |
|---|---|
list_projects, create_project, update_project |
projects, login gates, allowed hosts, app language, narration language and voice, the project's opening and ending (style, 3–10 s length, call to action, fade, narrated title) |
put_variables |
the demo user's credentials, encrypted |
get_guide_instructions |
the writing rules, the syntax and example guides; call it before writing a guide |
get_guide |
read a saved guide |
put_guide, validate_guide |
the auth guide and named main guides with an optional video_title for the opening; problems with line numbers and a corrected example |
start_run, get_run, list_runs, cancel_run |
recordings; start_run takes an optional voice and language for one video |
list_voices |
languages, voices, tiers and their relative cost |
get_credits, top_up |
balance, and a one-click top-up link when it runs short |
report_run_failure |
send us the evidence of a run that failed on our side, with your consent |
A failed run is free, and get_run reports how every step resolved and what was learned, so the fastest way to find out what the page really calls things is to run.
When it says no
insufficient_credits: the response carries a top-up link. The agent relays it; once you have paid it continues.requires_attestation:create_projectattests for you when you say the app is yours, a client's, or internal.check_limit_reached: today's free checks are used up; record instead, a failed recording costs nothing.free_minutes_used_for_app: this app already had free minutes on another account; recording it needs a plan.
The Claude Code plugin
Optional. The plugin adds the Screen Browser skill to Claude Code next to the same server: the
skill tells the agent when to reach for Screen Browser and walks it through the steps above. The
server already hands every client the writing rules through get_guide_instructions, so the
plugin is a convenience, not a requirement.
claude plugin marketplace add screenbrowser/skill
claude plugin install screenbrowser@screenbrowser
Installing the plugin registers the server too; skip the claude mcp add step above.