Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Capture and check localized App Store and Google Play screenshots from your AI agent.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified against the domain shotfleet.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.9) reached the registry 25 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, AI Deprecations
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
AI model shutdown dates, replacements, change feed and webhook alerts for 8 providers.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
This repo is the agent skills and MCP server config for shotfleet, a macOS command-line tool that captures your App Store and Google Play screenshots in every language your app ships, from one English Maestro flow (or your own XCUITest screenshot tests, since 0.1.6), and checks that each screenshot is really in the right language.
shotfleet itself is a paid, closed-source program with a free tier: check is free, run is free for up to 2 languages. The files here are MIT licensed and contain no shotfleet source; they only tell your AI coding agent how to use it. They match shotfleet 0.1.9.
The skills let your AI coding agent know how to install, set up, run and check shotfleet, and how to read the report:
| Skill | What it does |
|---|---|
shotfleet | the main one: which command to run, exit codes, --json, writing the flow, troubleshooting |
shotfleet-review | turns a check report into a fix list (which language to capture again, and if the fix is in the app or the flow) |
shotfleet-ci | adds shotfleet check to GitHub Actions or another CI |
The skills tell your agent what to type. The agent still needs shotfleet itself on your Mac:
curl -fsSL https://shotfleet.com/install.sh | sh
After installing shotfleet:
claude mcp add shotfleet -- shotfleet mcp
For any other MCP client, the command is shotfleet mcp (stdio). See the MCP server section below.
In a Claude Code session:
/plugin marketplace add noloman/shotfleet-skills
/plugin install shotfleet@shotfleet
Or from your shell:
claude plugin marketplace add noloman/shotfleet-skills
claude plugin install shotfleet@shotfleet
The plugin brings the three skills and the shotfleet MCP server (shotfleet mcp, with check, run and doctor). The MCP server only starts if shotfleet is installed; without it, /mcp shows it as failed and the skills still work. If you already ran shotfleet skill install, you'll see the skills twice. Remove one copy (~/.claude/skills/shotfleet*).
With GitHub CLI 2.90 or newer:
gh skill install noloman/shotfleet-skills --all --scope user
Pick the agent with --agent, for example --agent codex, --agent cursor, --agent gemini-cli or --agent claude-code. Leave out --scope user to install into the current project instead.
npx skills add noloman/shotfleet-skills --skill '*' -g
gemini skills install https://github.com/noloman/shotfleet-skills.git --path skills/shotfleet
gemini skills install https://github.com/noloman/shotfleet-skills.git --path skills/shotfleet-review gemini skills install https://github.com/noloman/shotfleet-skills.git --path skills/shotfleet-ci
Then you already have the skills too. This copies them where Claude Code, Codex, Cursor, Gemini CLI and Copilot look:
shotfleet skill install
Start a new agent session after any of these, then ask something like "check my fastlane screenshots with shotfleet".
shotfleet mcp runs a local stdio MCP server. It needs shotfleet installed on your Mac.
| Tool | What it does |
|---|---|
check | checks a folder of screenshots: each one shows its own language, no copies across languages, none missing, store size and count rules; returns a short summary |
doctor | says whether Maestro, Xcode and the Android SDK are ready, and what is missing; changes nothing |
run | captures screenshots in every language from a shotfleet.toml, then checks them; boots simulators and emulators, so it takes minutes |
Safety: no command written in your config runs over MCP unless the call passes hooks: true. Without it, run skips [hooks] and refuses a config with a [capture] build, [ios] simctl or [android] shell. run always installs and runs the config's app on the simulators, so only point it at a project you trust. check is not read-only: it writes its report (check.json and index.html) to a report folder, and never changes a screenshot.
The skills are free, MIT licensed. In shotfleet, check is free and run is free for up to 2 languages. run beyond 2 languages and export need a licence: shotfleet.com.
Never paste your licence key into an agent config, a chat, an MCP setting or a repo. Run this once yourself, in your own terminal:
shotfleet activate <your key>
After that your agent uses shotfleet and never sees the key. In CI, put the key in a secret called SHOTFLEET_KEY. Don't pass it with claude mcp add --env: it would end up in plain text in ~/.claude.json.
Write to me at hello@shotfleet.com. The files here are copied from the shotfleet source at each release, see SYNC.md.