Applify

Builds Streamlit apps from natural language requests.

CommunityOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • Build App: Build a Streamlit app from a natural language request. Describe what to build, optionally include data files, and the server handles everything: file upload, planning, code generation, and
  • List App: List built apps by viewer key. RULES: 1. Only set viewer_key if user explicitly mentioned it - Don't use placeholder values like "unused", "null", or empty strings 2. ALWAYS detect user's la

What data it sees

Do you need an account

An API key from the service settings is required

Builds Streamlit apps from natural language requests. Describe what you need — data dashboards, internal tools, utilities — and get a live preview URL with real-time build progress. Upload
data files (CSV, JSON, Excel) or connect to databases. Apps are built once and accessible from any browser or device via shareable URLs. Control access with viewer keys to restrict who can see each app. List and manage previously built apps. Supports MCP UI for rich embedded previews with build status tracking and app iframe.

How to connect

How to connect Applify to Claude

The server address to paste into Claude settings:

https://applify--omnivibes.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Applify to ChatGPT

The server address to paste into ChatGPT settings:

https://applify--omnivibes.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Applify to Cursor

The server address to paste into Cursor settings:

https://applify--omnivibes.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (2)

Raw names from tools/list. Only developers need these.

build_app Build a Streamlit app from a natural language request. Describe what to build, optionally include data files, and the server handles everything: file upload, planning, code generation, and deployment. Returns immediately with a JSON response containing app_id, status, message, and preview_url, plus an embedded UI resource for MCP UI clients. IMPORTANT: If your client renders MCP UI resources (iframes), do NOT paste the preview URL — the user already sees it embedded. Otherwise, include the preview URL so the user can open it in a browser. ASYNC BUILD: This tool returns immediately with a preview URL. The response includes _meta.wait_completion: true to signal the client that the build runs in the background. The preview iframe sends a prompt postMessage to the parent window when the build completes (or fails). Cancellation: If the client sends notifications/cancelled, the background build task detects it and stops gracefully. CLIENT _META FIELDS: Clients can pass context via params._meta (standard MCP location): - _meta.user_id: Client's user ID. Used as viewer_key if no explicit viewer_key is provided. - _meta.session_id: Client's conversation/thread ID (for tracking). Example with _meta: { "name": "build_app", "arguments": { "request": "Create a dashboard", "mode": "fast" }, "_meta": { "user_id": "user-123", "session_id": "thread-456" } } CRITICAL - viewer_key extraction: If the user's message contains "viewer_key" followed by a value (e.g., "viewer_key 123456" or "viewer_key=abc"), you MUST: 1. Extract the value and pass it as the viewer_key parameter 2. REMOVE it from the request text -- viewer_key is NOT an app feature IMPORTANT - Mode Selection: You should analyze the user's request and data to choose the appropriate mode: - mode="fast" (DEFAULT): Direct code generation, faster execution Use when: Clean structured data, simple clear requests, speed is priority Examples: "Show sales by region", "Create a bar chart from this CSV" - mode="thinking": Full reasoning with planning and validation, more robust Use when: Data needs cleaning, complex analysis, ambiguous requests Examples: "Analyze customer behavior patterns", "Find insights in messy data" IMPORTANT - Language Setting: You MUST detect the user's language and set the `language` parameter: - Chinese -> language="zh" - Japanese -> language="ja" - French -> language="fr" - German -> language="de" - Spanish -> language="es" - English or other -> language="en" Args: request: What to build (e.g., "Create a dashboard that shows sales data") mode: Build mode. Default: "fast" "fast" - Quick generation using unified agent (recommended for most cases) "thinking" - Full reasoning with planning and validation (for complex cases) language: UI language for progress page. MUST be set based on user's language. Supported: "en", "zh", "ja", "fr", "de", "es" app_id: Optional app ID to continue a previous app session files: Optional list of files to upload. Each file is a dict with: - filename: Name of the file (e.g., "data.csv") - content: File content as string (for CSV, JSON, TXT) - content_base64: Base64-encoded content (for binary files) - url: URL to download from (alternative to content) - description: Optional description of the data viewer_key: Optional. If the user provides a viewer_key in their message, pass it here. Groups apps under this key and requires it to view the preview URL. Returns: List containing: - TextContent with JSON: {"app_id", "name", "description", "preview_url", "created_at", "last_activity", "thumbnail_url"} - EmbeddedResource with UI preview page
list_app List built apps by viewer key. RULES: 1. Only set viewer_key if user explicitly mentioned it - Don't use placeholder values like "unused", "null", or empty strings 2. ALWAYS detect user's language and set the language parameter - Chinese → language="zh" - Japanese → language="ja" - French → language="fr" - German → language="de" - Spanish → language="es" - English → language="en" CLIENT _META FIELDS: If _meta.user_id is provided and no explicit viewer_key is set, _meta.user_id will be used as viewer_key automatically. Args: viewer_key: Optional. Only include if user mentioned a viewer key. language: REQUIRED. Detect from user's message language. Returns: JSON with app list + embedded gallery UI for MCP UI clients.