{"slug": "give-your-ai-assistant-a-video-studio-over-mcp-and-the-tool-pattern-that-keeps", "title": "Give your AI assistant a video studio over MCP (and the tool pattern that keeps it from burning your credits)", "summary": "A developer at Vidofy published a walkthrough for connecting Claude Code and Cursor to a remote MCP server that generates video, image and voice content, using browser-based OAuth sign-in instead of API keys in config files. The post's core argument is a tool-design pattern for paid MCP tools: split capability lookup (list_models, get_model) from cost estimation (estimate_cost) and execution (generate, get_status, get_result), so an assistant can price a request before committing credits. The author recommends the split for any metered MCP server, such as GPU time, SMS or renders, trading one extra round trip for a visible spending limit.", "body_md": "Most MCP demos read files or query databases. Those tools are cheap and reversible. The interesting design problem starts when a tool **spends money**: generating a video can cost real credits, and an assistant that calls it in a loop can empty a balance before you notice.\n\nThis post does two things. First, a five-minute setup that gives Claude Code or Cursor video, image and voice generation over a remote MCP server. Second, the tool design that makes it safe to hand an assistant a paid tool. The pattern works for any MCP server that costs money to run, not just this one.\n\n*Disclosure: the server in the examples is Vidofy's, which is our own product. The setup steps and the pattern are general.*\n\nA local MCP server is a process you install and run next to your client, usually with an API key in an environment variable. A **remote** server is just a URL. You add the URL, your client opens a browser sign-in, you approve it, and the client holds the permission. There is nothing to install and no key to paste into a config file or leave in a chat log.\n\nThat second part matters more than it sounds. A key in `mcp.json` ends up in dotfiles repos and screenshots. A permission you approved in the browser can be revoked per client, and the other clients keep working.\n\n```\nclaude mcp add --transport http vidofy https://vidofy.ai/mcp-app\n```\n\nThen, inside Claude Code, run `/mcp`, pick `vidofy`, and approve the sign-in in the browser that opens. After that, ask for an image or a video in the same session.\n\nAdd this to `~/.cursor/mcp.json`, or `.cursor/mcp.json` in your project:\n\n```\n{\n  \"mcpServers\": {\n    \"vidofy\": {\n      \"url\": \"https://vidofy.ai/mcp-app\"\n    }\n  }\n}\n```\n\nEnable it in Cursor's MCP settings and approve the sign-in. Claude.ai, Claude Desktop, ChatGPT, VS Code and Codex have the same flow with their own menus.\n\nSome clients cannot complete a browser sign-in because they expect to register themselves. For those, the same package runs locally against a personal token:\n\n```\n{\n  \"mcpServers\": {\n    \"vidofy\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@vidofy/mcp\"],\n      \"env\": { \"VIDOFY_TOKEN\": \"vmt_...\" }\n    }\n  }\n}\n```\n\nYou create that token once in your account settings. Same account, same balance.\n\nHere is what an assistant sees when you ask for \"a 9:16 clip of a cyclist riding through neon-lit rain, about 5 seconds, and tell me what it costs first\":\n\n`list_models`: looks for a model that does 9:16 at 5 seconds.` get_model`: reads that model's input contract (which fields exist, which are required, which durations are valid).`estimate_cost`: returns the credit cost `generate`, then `get_status`, then `get_result`: run it, follow it while it renders, return the file.\nThe important part is step 3. Generation is slow and costs money, so the server separates *deciding* from *doing*:\n\nIf you are building an MCP server around anything metered (GPU time, API calls, SMS, renders), copy that split: one tool to look up what is possible, one to price a specific request, one to commit. You give up one round trip and get back a spending limit the user can see.\n\nA few requests that work well in plain sentences:\n\nOn clients that support MCP Apps, such as Claude, the result arrives as a live card that updates while the clip renders. On a text-only client the same information comes back as text.\n\nThe connector page lists every client's exact steps, the model catalogue and the nine tools: [vidofy.ai/en/mcp](https://vidofy.ai/en/mcp). New accounts start with free credits, so you can run the flow above without paying anything first.\n\nIf you build MCP servers yourself, I would like to hear how you handle paid tools. Do you price first like this, or cap spend some other way?", "url": "https://wpnews.pro/news/give-your-ai-assistant-a-video-studio-over-mcp-and-the-tool-pattern-that-keeps", "canonical_source": "https://dev.to/brian_gorman_525aa72b980d/give-your-ai-assistant-a-video-studio-over-mcp-and-the-tool-pattern-that-keeps-it-from-burning-15b6", "published_at": "2026-11-03 22:18:39+00:00", "updated_at": "2026-11-03 22:22:16.587584+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-tools", "generative-ai", "developer-tools"], "entities": ["Vidofy", "Claude Code", "Cursor", "Anthropic", "MCP", "Claude Desktop", "ChatGPT", "VS Code"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/give-your-ai-assistant-a-video-studio-over-mcp-and-the-tool-pattern-that-keeps", "markdown": "https://wpnews.pro/news/give-your-ai-assistant-a-video-studio-over-mcp-and-the-tool-pattern-that-keeps.md", "text": "https://wpnews.pro/news/give-your-ai-assistant-a-video-studio-over-mcp-and-the-tool-pattern-that-keeps.txt", "jsonld": "https://wpnews.pro/news/give-your-ai-assistant-a-video-studio-over-mcp-and-the-tool-pattern-that-keeps.jsonld"}}