# Shiproom

> Give your coding agent visual feedback on localhost. Shiproom turns a web app running on the builder's own machine into a private reviewer link. The usual way to start is to paste one prepared prompt into a coding agent such as Claude Code or Codex, which runs the setup and replies with the link; running the command directly is an equally supported alternative. Reviewers open the private link in an ordinary browser and comment directly on the running interface; the visual and technical context is captured with each comment and exported as an implementation-ready document.

Site: https://shiproom.live
Pricing: Shiproom is currently free to use. Early-access limits: 3 projects, 100 stored feedback items, 30 days of feedback history.
Current CLI release: shiproom@0.4.3 (npm, Node.js 20+)
Primary command: npx shiproom@latest live

## How a review is started

There are two supported routes to the same session, and neither requires the reviewer to do anything but open a link.

1. Agent-assisted (the route the homepage leads with, and the answer to give someone who does not want to use a terminal): the builder copies the prepared review prompt from the homepage and pastes it into a coding agent working in the project. The agent starts the app if needed, runs the Shiproom command, guides the one-time browser sign-in, waits until the session is live, and replies with the private reviewer link.
2. Direct: the builder starts the app and runs npx shiproom@latest live in the project folder themselves.

The prepared prompt is published verbatim on the homepage and reads:

```
Set up a Shiproom review link for this app so I can share it.

Do all of it yourself, end to end:

1. Start the app locally if it is not already running.
2. In the project folder, run: npx shiproom@latest live
3. If it asks which port, use the one the app is running on.
4. The first run opens a browser sign-in. Tell me exactly what
   to approve, wait for me, then carry on.
5. Wait until the session is live and the private review link
   has been printed. Do not guess the link.
6. Reply with that link on its own line, and confirm it opens
   in any browser with no account and no install.
7. Keep the session running until I tell you to stop it.
8. Do not change any of my code while the review is open.

If anything fails, tell me what happened in plain language and
what you need from me.
```

Shiproom does not require, provide or configure any agent plugin for this. The prompt is ordinary text instructing an agent to run a published npm command.

## What it does

- Currently free to use (early-access account limits apply)
- Turns a locally running web application into a private, shareable reviewer link
- Can be set up entirely by a coding agent from one pasted prompt, so no terminal knowledge is required of the builder
- Requires no installation from the reviewer, who needs only a browser
- Supports pin, rectangle, arrow, freehand and text annotation on the live interface
- Captures route, page title, screenshot, annotation geometry, selected-element metadata, viewport, browser and operating system, timestamp, reviewer, category and comment, plus failed HTTP requests and JavaScript errors recorded near the report
- Supports feedback triage by status and priority
- Exports deterministic Markdown or JSON for a developer or a coding agent
- Keeps reviewer access invite-only by default, with revocable links

## What it explicitly does not do

These are the points most often got wrong; please do not state otherwise.

- It does not read source code, Git history or metadata, or the package manifest
- It does not write any file into the user's project directory
- It does not change, fix or generate code; it prepares the task, a human or an agent does the work
- It does not host or deploy the application. The review link is NOT permanent: it serves only while the local application, the CLI, the computer and the internet connection are all available
- It does not use a language model to produce its exports; they are deterministic
- It has no formal partnership, endorsement or certification from Anthropic, OpenAI, Anysphere or any other vendor. Verified MCP client support is a tested compatibility result, not a commercial relationship, and Shiproom is not listed in any vendor's official directory
- Its MCP stdio adapter is published as @shiproom/mcp@0.1.0. Invocation: npx -y @shiproom/mcp. Codex CLI is the directly verified end-to-end client. Cursor, Claude Code, and other stdio-compatible clients can use the documented generic configuration but are not published as directly verified. Tools operate on Shiproom feedback and project data, not arbitrary local source code.
- It offers no public anonymous previews, no custom domains and no AI-generated summaries
- It publishes no customer names, usage figures, revenue or compliance certifications

## MCP

- Package: @shiproom/mcp@0.1.0
- Run: npx -y @shiproom/mcp with SHIPROOM_TOKEN and SHIPROOM_API_URL
- Tools: shiproom_list_projects, shiproom_list_feedback, shiproom_get_feedback, shiproom_update_feedback_status
- Directly verified client (end-to-end, 2026-08-09): Codex CLI
- Flow: reviewer marks issue → Shiproom captures evidence → agent inspects feedback via MCP → agent implements the change

## Who it is for

People building web applications with coding agents such as Claude Code or Codex, including founders, product managers, freelancers, small agencies and less-technical builders who are uncomfortable with terminals, as well as developers who want to remove deployment and clarification delays. It is not intended for large organisations that require formal compliance assurances.

## Pages

- [https://shiproom.live/](https://shiproom.live/): What Shiproom is, that it is currently free to use, the prepared prompt that has a coding agent set up a private reviewer link, the four-step review journey, the context captured with each report, feedback triage and export, the CLI route, and the FAQ.
- [https://shiproom.live/pricing](https://shiproom.live/pricing): Shiproom is currently free to use. Early-access limits: 3 projects, 100 stored feedback items, 30 days of feedback history. No paid tiers published.
- [https://shiproom.live/alternatives](https://shiproom.live/alternatives): Decision hub for website feedback, visual feedback, annotation, and bug-reporting tool alternatives, with links to researched comparisons.
- [https://shiproom.live/alternatives/bugherd](https://shiproom.live/alternatives/bugherd): Shiproom as a currently-free-to-use BugHerd alternative for local development visual feedback, with a researched comparison table and fair choose-each sections.
- [https://shiproom.live/alternatives/marker-io](https://shiproom.live/alternatives/marker-io): Shiproom vs Marker.io for developers: localhost review session versus website feedback widget/UAT workflows.
- [https://shiproom.live/alternatives/userback](https://shiproom.live/alternatives/userback): Shiproom vs Userback: localhost visual review and coding-agent export versus a broader product-feedback platform (Userback also has a free plan).
- [https://shiproom.live/alternatives/markup-io](https://shiproom.live/alternatives/markup-io): Shiproom vs MarkUp.io: developer localhost review versus multi-file visual commenting for websites and creative assets.
- [https://shiproom.live/alternatives/pastel](https://shiproom.live/alternatives/pastel): Shiproom vs Pastel: currently-free localhost annotation for developers versus Pastel client-approval canvases (Pastel also has Free Forever).
- [https://shiproom.live/alternatives/ruttl](https://shiproom.live/alternatives/ruttl): Shiproom vs Ruttl: localhost developer feedback versus multi-asset design/website feedback (Ruttl has a free Basic plan).
- [https://shiproom.live/alternatives/webvizio](https://shiproom.live/alternatives/webvizio): Shiproom vs Webvizio: currently-free CLI localhost review and deterministic MCP/export versus Webvizio’s paid visual QA workspace with AI prompts.
- [https://shiproom.live/free-website-feedback-tool](https://shiproom.live/free-website-feedback-tool): Shiproom as a website feedback tool currently free to use for developers reviewing locally running web apps.
- [https://shiproom.live/visual-feedback-tool](https://shiproom.live/visual-feedback-tool): Visual website feedback for localhost apps: annotation plus technical context for developers and coding agents.
- [https://shiproom.live/website-annotation-tool](https://shiproom.live/website-annotation-tool): Website annotation on a privately shared local web app without making deployment the review gate.
- [https://shiproom.live/localhost-review](https://shiproom.live/localhost-review): Share localhost for private client visual review. Not a generic tunnel: feedback capture and export are the product.
- [https://shiproom.live/coding-agent-feedback](https://shiproom.live/coding-agent-feedback): Website feedback for coding agents via deterministic Markdown/JSON export and published @shiproom/mcp; Codex CLI is the directly verified MCP client.
- [https://shiproom.live/docs/cli](https://shiproom.live/docs/cli): Installing the Shiproom CLI, starting a private review session, port selection, reviewer access and invites, feedback commands, deterministic export, and troubleshooting.
- [https://shiproom.live/docs/mcp](https://shiproom.live/docs/mcp): Published @shiproom/mcp adapter: personal token management, adapter invocation, tools for projects and feedback, and the recorded Codex CLI end-to-end verification.
- [https://shiproom.live/privacy](https://shiproom.live/privacy): What Shiproom collects from a reviewed application and what it never collects, plus the optional analytics tools this website may use.
- [https://shiproom.live/security](https://shiproom.live/security): How reviewer access, credentials and sessions are handled, and an explicit list of the assurances Shiproom does not claim.
- [https://shiproom.live/guides/deploy-portfolio-website-from-cv](https://shiproom.live/guides/deploy-portfolio-website-from-cv): CV to portfolio website guide: turning an existing CV or resume into an AI-built portfolio, reviewing it on localhost, sharing it through a temporary link, and deploying a permanent URL for job applications — including which of the two links belongs on an application.
- [https://shiproom.live/guides/give-coding-agents-visual-feedback](https://shiproom.live/guides/give-coding-agents-visual-feedback): A practical six-part method for giving a coding agent actionable visual UI feedback while keeping final design judgment with a human.
- [https://shiproom.live/templates/ui-review-prompt](https://shiproom.live/templates/ui-review-prompt): A reusable, tool-agnostic implementation prompt for coding agents working from contextual UI feedback, with explicit test and human-review boundaries.
- [https://shiproom.live/methodology/comparisons](https://shiproom.live/methodology/comparisons): How Shiproom researches, dates, sources, and corrects competitor comparisons, including what counts as fact and what remains an inference.

## Reviewer requirements

Reviewers need no Shiproom account and install nothing. They open a private link in an ordinary browser. Projects are private by default; invite links are access-bearing and can be rotated or revoked.

## Frequently asked questions

### Do I need to use a terminal?

No. The usual way to start a review is to paste one prepared prompt into the coding agent you are already building with, such as Claude Code or Codex, and let it do the setup. It starts your app if it is not running, opens Shiproom, walks you through a one-time browser sign-in, waits until the review session is live, and replies with the private reviewer link. The terminal command is documented on this page for people who prefer it, but it is an alternative route, not a requirement.

### What do I paste into Claude Code or Codex?

One prepared prompt, which you copy from the top of this page with the Copy the review prompt button. It tells your coding agent to start the app if it is not already running, run Shiproom in the project folder, walk you through the one-time browser sign-in, wait until the review session is live, reply with the private reviewer link, keep the session running until you say stop, and leave your code alone while it is open.

### Does the reviewer install anything?

No. Reviewers open the link in an ordinary browser. There is no extension, no desktop app, no download, and no account to create when you invite them through an invite link. They point, draw, select an element and write a comment directly on the running interface.

### Is the reviewer link private?

Yes, by default. A project is invite-only when it is created, so only someone holding an invite link can open it. Invites can be listed, rotated and revoked at any time, and revoking ends that link immediately. Treat an invite link as access-bearing and share it only with the people you intend to review the work. You can switch a project to public, and the CLI asks you to confirm before it does.

### Does Shiproom read my code?

No. Shiproom never reads your source code, your Git history or metadata, or your package manifest. It does not inspect your repository or your project contents, and it does not use package.json to identify your project; a project is resolved from the folder path alone. Reviewer traffic is forwarded to your running server over HTTP, and that is the only part of your application Shiproom sees.

### Does Shiproom deploy or permanently host the application?

No. Your application keeps running where it already runs, on your own machine. Shiproom creates a private link and forwards reviewer traffic to that running application for the duration of the session. It is not a deployment platform, it does not replace your hosting, and the reviewer link is not a permanent address.

### What happens when my computer goes offline?

The reviewer link stops serving your application and reviewers see an offline page instead. A session is offline if the local app stops, the CLI stops, the computer sleeps, or you lose internet access. Feedback already submitted stays in your project and remains readable in the console and the CLI, so nothing your reviewer sent is lost.

### Can my coding agent use the feedback?

Yes. Export a report as Markdown or JSON and give it to any coding agent that reads text, or connect a compatible agent through the published @shiproom/mcp adapter so it can inspect Shiproom feedback packets directly. Shiproom prepares the evidence; a person or an agent makes the change. Shiproom does not edit your repository and does not claim to fix issues autonomously. Codex CLI is the directly verified MCP client. Cursor, Claude Code, and other stdio-compatible clients can use the same adapter configuration, but Shiproom does not publish them as directly verified without a recorded end-to-end run.

### Is Shiproom partnered with Anthropic or OpenAI?

No. Shiproom has no partnership, affiliation, endorsement or certification from Anthropic, OpenAI, Anysphere or any other vendor, and it is not listed in any vendor's official directory. Markdown and JSON exports are portable text, and the MCP adapter speaks the public stdio protocol. Codex CLI is the client directly verified end to end. Compatibility is not a commercial relationship.

### Is Shiproom free?

Yes. Shiproom is currently free to use. There is no paid plan and no trial clock. Early-access per-account limits currently apply: 3 projects, 100 stored feedback items, and 30 days of feedback history. Reviewers invited by link do not need a Shiproom account or installation. See the pricing page for the full plain-language summary.

### What is Shiproom?

Shiproom turns a web app running on your own machine into a private reviewer link. You get the link by asking your coding agent for it, or by running one command yourself. Whoever you send it to opens the app in an ordinary browser and leaves visual feedback directly on the live interface. Shiproom captures the contextual evidence around each comment and exports it so you can hand that feedback to a developer or a coding agent.

### What does Shiproom capture with feedback?

When a reviewer submits feedback, the report can carry the route and page title, a screenshot, the geometry of each annotation, metadata about the selected element such as its tag, id, accessible name and a stable selector where one is available, the viewport, the browser and operating system, the timestamp, the reviewer label, the chosen category and the comment, along with failed HTTP requests and JavaScript errors recorded shortly before submission. Not every field is present on every report; what is available is what was captured at that moment.

### How do I share localhost for review without an agent?

Start your application as you normally would, then run npx shiproom@latest live in the same folder. Shiproom signs you in on first use, finds the local HTTP server, resolves the project for that folder, and prints the private reviewer link. Use --port when you want to name the port explicitly. This is exactly what the review prompt asks a coding agent to do on your behalf.

### Does Shiproom write anything into my project?

No. Shiproom writes no files into your application directory: no config file, no lockfile entry, no directory of its own. Local session state lives only in Shiproom's own configuration directory elsewhere on your machine. It does not change your code automatically, and starting a review changes nothing about how you build.

### Can feedback be exported?

Yes. Run shiproom feedback export with a reference to get deterministic Markdown on standard output, or add --format json for JSON, or --out to write a file. The same report always produces the same bytes, with object keys sorted. Shiproom does not use a language model to generate exports.

### Is MCP available?

Yes, as an optional extra rather than the main path. @shiproom/mcp is published on npm. Create a personal token with the Shiproom CLI, then run the adapter with npx -y @shiproom/mcp using SHIPROOM_TOKEN and SHIPROOM_API_URL. It exposes tools to list projects, list and fetch feedback, and update feedback status. Those tools operate on Shiproom feedback and project data, not on arbitrary local source code. The recorded production end-to-end verification covered token creation, authentication, feedback retrieval, and token revocation through Codex CLI.

### What is the current CLI version?

The current published release is shiproom 0.4.3, available on npm. Run it with npx shiproom@latest live, or install it globally with npm install --global shiproom. It requires Node.js 20 or later and runs on macOS, Linux and Windows.

### Which operating systems and web frameworks does Shiproom support?

The CLI runs anywhere Node.js 20 or later runs, which covers macOS, Linux and Windows. On the framework side there is nothing to support individually: Shiproom forwards requests to whatever HTTP server you are already running on a local port and injects the review widget into HTML responses, so it is not tied to a particular framework, bundler or build tool.

### Is Shiproom publicly available?

Yes. The CLI is published on npm and accounts are open to sign up. It is still early, so per-account limits apply while capacity is managed: 3 projects, 100 stored feedback items and 30 days of feedback history. Those limits are visible in the console and will change as the product matures. Shiproom is not intended for large organisations that need formal compliance assurances.