From efa854f7c7c6736ae670275e2fa3daa4008a5471 Mon Sep 17 00:00:00 2001 From: Ace Data Cloud Dev Date: Fri, 20 Mar 2026 02:27:53 +0800 Subject: [PATCH] docs: prioritize hosted MCP endpoints in README - Restructure Quick Start to put cloud-hosted server first as recommended option - Add clear API token acquisition steps with direct links - Add configs for Claude Desktop, Cursor, Windsurf, VS Code, JetBrains - Move local installation to 'Alternative' section - Add remotes field to server.json for MCP Registry discovery --- README.md | 149 +++++++++++++++++++++++++--------------------------- server.json | 8 ++- 2 files changed, 79 insertions(+), 78 deletions(-) diff --git a/README.md b/README.md index 557eadf..996d060 100644 --- a/README.md +++ b/README.md @@ -24,123 +24,82 @@ Generate AI videos directly from Claude, VS Code, or any MCP-compatible client. ## Quick Start -### 1. Get API Token +### 1. Get Your API Token -Get your API token from [AceDataCloud Platform](https://platform.acedata.cloud): +1. Sign up at [AceDataCloud Platform](https://platform.acedata.cloud) +2. Go to the [API documentation page](https://platform.acedata.cloud/documents/5bd3597d-1ff8-44ad-a580-b66b48393e7f) +3. Click **"Acquire"** to get your API token +4. Copy the token for use below -1. Sign up or log in -2. Navigate to [Luma Videos API](https://platform.acedata.cloud/documents/5bd3597d-1ff8-44ad-a580-b66b48393e7f) -3. Click "Acquire" to get your token +### 2. Use the Hosted Server (Recommended) -### 2. Install +AceDataCloud hosts a managed MCP server — **no local installation required**. -```bash -# Clone the repository -git clone https://github.com/AceDataCloud/mcp-luma.git -cd mcp-luma - -# Install with pip -pip install -e . - -# Or with uv (recommended) -uv pip install -e . -``` - -### 3. Configure +**Endpoint:** `https://luma.mcp.acedata.cloud/mcp` -```bash -# Copy example environment file -cp .env.example .env - -# Edit with your API token -echo "ACEDATACLOUD_API_TOKEN=your_token_here" > .env -``` +All requests require a Bearer token. Use the API token from Step 1. -### 4. Run +#### Claude Desktop -```bash -# Run the server -mcp-luma - -# Or with Python directly -python main.py -``` - -## Claude Desktop Integration - -Add to your Claude Desktop configuration: - -**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` -**Windows**: `%APPDATA%\Claude\claude_desktop_config.json` +Add to your config (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS): ```json { "mcpServers": { "luma": { - "command": "mcp-luma", - "env": { - "ACEDATACLOUD_API_TOKEN": "your_api_token_here" + "type": "streamable-http", + "url": "https://luma.mcp.acedata.cloud/mcp", + "headers": { + "Authorization": "Bearer YOUR_API_TOKEN" } } } } ``` -Or if using uv: +#### Cursor / Windsurf + +Add to your MCP config (`.cursor/mcp.json` or `.windsurf/mcp.json`): ```json { "mcpServers": { "luma": { - "command": "uv", - "args": ["run", "--directory", "/path/to/mcp-luma", "mcp-luma"], - "env": { - "ACEDATACLOUD_API_TOKEN": "your_api_token_here" + "type": "streamable-http", + "url": "https://luma.mcp.acedata.cloud/mcp", + "headers": { + "Authorization": "Bearer YOUR_API_TOKEN" } } } } ``` -## Remote HTTP Mode (Hosted) - -AceDataCloud hosts a managed MCP server that you can connect to directly — **no local installation required**. +#### VS Code (Copilot) -**Endpoint**: `https://luma.mcp.acedata.cloud/mcp` - -All requests require a Bearer token in the `Authorization` header. Get your token from [AceDataCloud Platform](https://platform.acedata.cloud). - -### Claude Desktop (Remote) +Add to your VS Code MCP config (`.vscode/mcp.json`): ```json { - "mcpServers": { + "servers": { "luma": { "type": "streamable-http", "url": "https://luma.mcp.acedata.cloud/mcp", "headers": { - "Authorization": "Bearer your_api_token_here" + "Authorization": "Bearer YOUR_API_TOKEN" } } } } ``` -### Cursor / VS Code - -In your MCP client settings, add: +Or install the [Ace Data Cloud MCP extension](https://marketplace.visualstudio.com/items?itemName=acedatacloud.acedatacloud-mcp) for VS Code, which bundles all 11 MCP servers with one-click setup. -- **Type**: `streamable-http` -- **URL**: `https://luma.mcp.acedata.cloud/mcp` -- **Headers**: `Authorization: Bearer your_api_token_here` - -### JetBrains IDEs - -Install the [Luma MCP plugin](https://plugins.jetbrains.com/plugin/com.acedatacloud.mcp.luma) from the JetBrains Marketplace, or configure manually: +#### JetBrains IDEs 1. Go to **Settings → Tools → AI Assistant → Model Context Protocol (MCP)** -2. Click **Add** and select **HTTP** -3. Paste this configuration: +2. Click **Add** → **HTTP** +3. Paste: ```json { @@ -148,35 +107,71 @@ Install the [Luma MCP plugin](https://plugins.jetbrains.com/plugin/com.acedatacl "luma": { "url": "https://luma.mcp.acedata.cloud/mcp", "headers": { - "Authorization": "Bearer your_api_token_here" + "Authorization": "Bearer YOUR_API_TOKEN" } } } } ``` -### cURL Test +#### cURL Test ```bash # Health check (no auth required) curl https://luma.mcp.acedata.cloud/health -# MCP initialize (requires Bearer token) +# MCP initialize curl -X POST https://luma.mcp.acedata.cloud/mcp \ -H "Content-Type: application/json" \ -H "Accept: application/json" \ - -H "Authorization: Bearer your_api_token_here" \ + -H "Authorization: Bearer YOUR_API_TOKEN" \ -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' ``` -### Self-Hosting with Docker +### 3. Or Run Locally (Alternative) + +If you prefer to run the server on your own machine: + +```bash +# Install from PyPI +pip install mcp-luma +# or +uvx mcp-luma + +# Set your API token +export ACEDATACLOUD_API_TOKEN="your_token_here" + +# Run (stdio mode for Claude Desktop / local clients) +mcp-luma + +# Run (HTTP mode for remote access) +mcp-luma --transport http --port 8000 +``` + +#### Claude Desktop (Local) + +```json +{ + "mcpServers": { + "luma": { + "command": "uvx", + "args": ["mcp-luma"], + "env": { + "ACEDATACLOUD_API_TOKEN": "your_token_here" + } + } + } +} +``` + +#### Docker (Self-Hosting) ```bash docker pull ghcr.io/acedatacloud/mcp-luma:latest docker run -p 8000:8000 ghcr.io/acedatacloud/mcp-luma:latest ``` -Clients connect with their own Bearer token — the server extracts the token from each request's `Authorization` header and uses it for upstream API calls. +Clients connect with their own Bearer token — the server extracts the token from each request's `Authorization` header. ## Available Tools diff --git a/server.json b/server.json index 76ede24..aa977b3 100644 --- a/server.json +++ b/server.json @@ -26,5 +26,11 @@ ] } ], - "websiteUrl": "https://platform.acedata.cloud" + "websiteUrl": "https://platform.acedata.cloud", + "remotes": [ + { + "type": "streamable-http", + "url": "https://luma.mcp.acedata.cloud/mcp" + } + ] }