Designpin MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 58 installs a week from npm. Last commit 2 May 2026.
Push HTML prototypes to DesignPin for team review and pull reviewer feedback into your AI.
Today is the operative word: we check Designpin MCP Server every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 designpin-mcp-server -- npx -y @designpin/mcp-server
{
"mcpServers": {
"designpin-mcp-server": {
"command": "npx",
"args": [
"-y",
"@designpin/mcp-server"
]
}
}
}
[mcp_servers.designpin-mcp-server]
command = "npx"
args = ["-y", "@designpin/mcp-server"]
{
"mcpServers": {
"designpin-mcp-server": {
"command": "npx",
"args": [
"-y",
"@designpin/mcp-server"
]
}
}
}
{
"servers": {
"designpin-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@designpin/mcp-server"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
DESIGNPIN_API_KEY (DesignPin project-scoped API key. Generate at https://designpin.pro under Project Settings. Required for uploadVersion and listComments tools; not required for createShareLink), DESIGNPIN_PROJECT_ID (Firestore project document ID the API key is scoped to. Required when using uploadVersion or listComments), DESIGNPIN_BASE_URL (API base URL. Defaults to https://designpin.pro. Override only for testing against a staging or alternate host).
Share prototypes for team review: publish HTML, reviewers pin notes, pull feedback back to apply.
Prototypes made of HTML screens and the review notes designers dictate, ready for your AI to apply.
Translate HTML prototypes into Figma using your design system's real components and tokens.
A home for your agent's HTML artifacts - publish, pull, share and review them over MCP.
Hand-drawn whiteboard for system design mock interviews; your AI watches, asks and gives feedback.
Deploy prototypes and collect team feedback from Claude Code, Cursor, or any MCP client.
Guided walkthroughs that play on your real prototype, with your team's feedback for your agent.
Manage feedback, ratings, surveys, changelogs, and review tasks in your SeggWat projects.
Answers built from our own checks of this server.