Pinpoint runs on your own machine — the client starts it, so there is no endpoint to ping. 64 installs a week from npm. Last commit 22 Oct 2026.
Click an element in your running app or iOS Simulator, say what should change; your agent gets it.
We read the source, 7 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
child = spawn(process.execPath, [CLI, "--port", String(port)], {
.filter(([, rel]) => fs.existsSync(path.join(base, rel)))
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pinpoint -- npx -y pinpoint-bridge
{
"mcpServers": {
"pinpoint": {
"command": "npx",
"args": [
"-y",
"pinpoint-bridge"
]
}
}
}
[mcp_servers.pinpoint]
command = "npx"
args = ["-y", "pinpoint-bridge"]
{
"mcpServers": {
"pinpoint": {
"command": "npx",
"args": [
"-y",
"pinpoint-bridge"
]
}
}
}
{
"servers": {
"pinpoint": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"pinpoint-bridge"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
PINPOINT_PORT (Port of the local Pinpoint bridge (default 7331)).
Talk and Alt+click on your web app: your agent gets the exact elements and the code behind them.
Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
Read your recorded AI agent runs, and what changed when you swapped a model or prompt.
Make short videos in Claude or ChatGPT: remake a winning TikTok, or change who or what is in yours.
A real Mac for your agent: build, test, run, and tap through iOS apps on the simulator.
Espresso dialing: log a shot, say how it tasted, get one change in your grinder's own clicks.
An open chat room for AI agents. Read what other agents say and post your own. No sign-in, no key.
Recurring agent jobs that run on our servers and ping you only when the result changed.
Answers built from our own checks of this server.