PromptUI
REMOTE · WWW.PROMPTUI.CO · SCANNED SEP 21
Build a working web app from a prompt, then deploy it to a live URL.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security89
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token. See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1010 tokens (~91/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management52
- Stability check failed: schema churn in the 18 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
How do I install the PromptUI MCP server?
PromptUI is a hosted endpoint at https://www.promptui.co/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · www.promptui.co
claude mcp add --transport http co-promptui-promptui 'https://www.promptui.co/api/mcp'
{
"mcpServers": {
"co-promptui-promptui": {
"url": "https://www.promptui.co/api/mcp"
}
}
} {
"servers": {
"co-promptui-promptui": {
"type": "http",
"url": "https://www.promptui.co/api/mcp"
}
}
} [mcp_servers.co-promptui-promptui] url = "https://www.promptui.co/api/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"co-promptui-promptui": {
"type": "remote",
"url": "https://www.promptui.co/api/mcp",
"enabled": true
}
}
} openclaw mcp add co-promptui-promptui --url 'https://www.promptui.co/api/mcp' --transport streamable-http
mcp_servers:
co-promptui-promptui:
url: "https://www.promptui.co/api/mcp" {
"McpServers": {
"co-promptui-promptui": {
"Transport": "http",
"Url": "https://www.promptui.co/api/mcp"
}
}
} assistant mcp add co-promptui-promptui -t streamable-http -u 'https://www.promptui.co/api/mcp'
{
"mcpServers": {
"co-promptui-promptui": {
"type": "http",
"url": "https://www.promptui.co/api/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 45 to 48.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 38 to 42.
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 28 to 32.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 22 to 25.
- 12 Sept 26 0
- Server version: 0.2.0 → 0.3.0 functional
- “gtm_generate_content” reworded the description of “deliverableType” cosmetic
- 11 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 14 to 17.
- 9 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 11.
- 8 Sept 26 0
- Tool “gtm_get_analytics” rewrote its description, which is the text the model reads security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Sept 2026 · Probed https://www.promptui.co/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=www.promptui.co | CN=YR1,O=Let's Encrypt,C=US | 18 Aug 2026 | 16 Nov 2026 | RSA 2048 | SHA256-RSA | 6f3dce0d9548ea50c2efa869b7e6a161756 |
| SANs: www.promptui.co | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.promptui.co. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| co. | present | 7786 | 8 | Verified |
| promptui.co. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Challenged, unverified
The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.
| Result | Challenged, unverified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer
Bearer| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net https://cdn.tailwindcss.com https://clerk.promptui.co https://*.clerk.accounts.dev https://challenges.cloudflare.com https://js.stripe.com https://us.i.posthog.com https://us-assets.i.posthog.com https://vercel.live https://*.vercel.live https://*.staticblitz.com https://w-corp-staticblitz.com https://connect.facebook.net https://www.googletagmanager.com https://www.googleadservices.com https://googleads.g.doubleclick.net https://files.tlt-cdn.com; style-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net https://cdn.tailwindcss.com; img-src 'self' data: blob: https://promptui.co https://www.promptui.co https://*.supabase.co https://*.stripe.com https://img.clerk.com https://api.qrserver.com https://blob.vercel-storage.com https://*.blob.vercel-storage.com https://api.dicebear.com https://images.pexels.com https://www.facebook.com https://www.google.com https://googleads.g.doubleclick.net https://www.googleadservices.com https://*. |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Protected resource metadata
| Retrieved | No |
|---|---|
| Problem | no_resource_metadata |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.promptui.co/api/mcp | Verified | 200 | |
| http (plaintext) | http://www.promptui.co/api/mcp | HTTPS enforced | 308 | https://www.promptui.co/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
build_app Build a web app ~132
Build a working web app from a prompt with PromptUI. Starts an asynchronous build (costs credits from the authenticated account) and returns a buildId — poll get_build_status for progress and the preview link.
| Name | Type | Req | Description |
|---|---|---|---|
| _confirmed | boolean | – | Set to true only after the user has explicitly approved this exact write or credit-spending action. |
| framework | string | – | Output framework: 'react-spa' (default) or 'nextjs-app' |
| mode | string | – | Build mode: 'quality' (default) or 'fast' |
| prompt | string | yes | What to build, in plain language |
No output schema declared.
No examples provided.
deploy_app Deploy app to a live URL ~78
Deploy a completed PromptUI build to a live URL. The first deploy of each app is charged; redeploying that same app is free.
| Name | Type | Req | Description |
|---|---|---|---|
| _confirmed | boolean | – | Set to true only after the user has explicitly approved this exact write or credit-spending action. |
| buildId | string | yes | The buildId of a completed build |
No output schema declared.
No examples provided.
echo Echo (connection test) ~27
Echo back the input (for testing MCP integration)
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | Message to echo |
No output schema declared.
No examples provided.
get_build_status Check build status ~57
Check the status of a PromptUI build started with build_app. Returns building / needs_clarification / completed (with a shareable previewUrl) / failed.
| Name | Type | Req | Description |
|---|---|---|---|
| buildId | string | yes | The buildId returned by build_app |
No output schema declared.
No examples provided.
gtm_generate_content Draft marketing content ~216
Generate and persist a new GTM content draft for the authenticated user.
| Name | Type | Req | Description |
|---|---|---|---|
| _confirmed | boolean | – | Set to true only after the user has explicitly approved this exact write or credit-spending action. |
| appSource | string | – | promptui | custom session id |
| campaignId | string | – | Optional campaign id |
| channel | string | – | Delivery channel. One of: x|linkedin|facebook|instagram|youtube|email|web |
| contentClass | string | – | Content class. One of: product_led|brand_led|domain_led|offer_led |
| count | number | – | Number of variants to generate (1-20) |
| deliverableType | string | – | Deliverable type. One of: post|thread|launch_pack|bio|promo_campaign|educational_series|landing_copy|visual_brief|seo_blog_post|seo_landing_page|llms_txt |
| language | string | – | Optional language |
| operatorPrompt | string | – | Optional operator instruction for the generator |
No output schema declared.
No examples provided.
gtm_get_analytics Get marketing analytics ~43
Read current PromptUI GTM channel analytics and workspace-scoped verified commerce outcomes. Attribution is reported separately from causality; unavailable spend/cost coverage stays explicit.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
gtm_list_content List marketing content ~105
List GTM queue items for the authenticated PromptUI user.
| Name | Type | Req | Description |
|---|---|---|---|
| campaignId | string | – | Optional campaign id filter |
| channel | string | – | Optional channel filter: x|linkedin|facebook|instagram|youtube|email|web |
| limit | number | – | Maximum number of items (default 20, max 100) |
| status | string | – | Optional status filter: draft|in_review|approved|vetoed|scheduled|published|archived |
No output schema declared.
No examples provided.
gtm_publish_content Publish a post to a connected channel ~113
Publish one GTM content item to a connected social platform.
| Name | Type | Req | Description |
|---|---|---|---|
| _confirmed | boolean | – | Set to true only after the user has explicitly approved this exact write or credit-spending action. |
| contentId | string | yes | GTM content id to publish |
| igUserId | string | – | Optional Instagram user id target |
| pageId | string | – | Optional LinkedIn/Facebook page target id |
| platform | string | – | Optional platform override: x|linkedin|facebook|instagram|tiktok |
No output schema declared.
No examples provided.
list_builds List your builds ~40
List the authenticated user's recent PromptUI builds with their statuses.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Maximum builds to return (default 10, max 50) |
No output schema declared.
No examples provided.
shadcn_ui Get a shadcn/ui component ~112
Get production-quality shadcn/ui component code pre-adapted for the Sandpack preview environment. Available components: accordion, dropdown_menu, dialog, sheet, tooltip, progress, separator, scroll_area, skeleton, alert. Returns ready-to-use JS code with correct imports. Use this instead of building complex UI primitives from scratch.
| Name | Type | Req | Description |
|---|---|---|---|
| component | string | yes | Component name to fetch. One of: accordion, dropdown_menu, dialog, sheet, tooltip, progress, separator, scroll_area, skeleton, alert |
No output schema declared.
No examples provided.
web_scout Search and read the web ~87
Research the live web: search for information, read documentation, fetch API references, or verify library usage. Returns structured findings as markdown.
| Name | Type | Req | Description |
|---|---|---|---|
| goal | string | yes | What to research or look up on the web |
| maxPages | number | – | Max pages to fetch content from |
| urls | array | – | Specific URLs to visit (optional — if omitted, will search the web) |
No output schema declared.
No examples provided.
What is the PromptUI MCP server?
PromptUI is an MCP server listed in the public MCP registry as co.promptui/promptui. Build a working web app from a prompt, then deploy it to a live URL. This page covers its hosted endpoint (https://www.promptui.co/api/mcp).
Is the PromptUI MCP server safe to use?
PromptUI scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the PromptUI MCP server expose?
PromptUI exposes 11 tools: echo, web_scout, shadcn_ui, build_app, get_build_status, and 6 more. Their descriptions and schemas cost roughly 1,010 tokens of context every time the server is loaded.
Does the PromptUI MCP server require authentication?
Yes. PromptUI asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the PromptUI MCP server still maintained?
PromptUI is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.