MCP.so
登录

Rendley MCP Server

@rendleyhq

基本信息

分类

其他

传输方式

stdio

作者

rendleyhq

提交者

Grigore Budac

关于 Rendley MCP Server

Rendley’s MCP server gives your AI client a full video editor. Connect it once, then create and edit video by describing what you want, in the same chat you already work in. The client uses your own footage, your brand kit, and Rendley’s stock and AI tools, and hands back a finis

Rendley MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "rendley-mcp": {
      "command": "bun",
      "args": [
        "dev",
        "#",
        "http://localhost:8787"
      ]
    }
  }
}

Rendley MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Rendley MCP?

Rendley MCP is a Model Context Protocol server that gives an AI assistant a full video editor. It connects to the hosted Rendley editor and API, allowing users to create and edit videos by describing what they want in their chat interface. It is designed for anyone who wants to generate or edit videos conversationally.

How to use Rendley MCP?

Users can either connect to the hosted server at https://mcp.rendley.com/mcp or self-host the server using Bun or Docker. Clients authenticate via OAuth sign‑in or an API key sent as a Bearer header. Once connected, ask the assistant what it can do, then describe the desired video.

Key features of Rendley MCP

  • Connect once and create/edit videos by describing them.
  • Drives the hosted Rendley editor in a browser.
  • Supports both remote MCP and plain HTTP REST endpoints.
  • Authenticates per request with the caller’s own API key or OAuth.
  • Self-hostable; single‑tenant per instance.
  • Browser launches lazily; concurrent requests reuse separate tabs.

Use cases of Rendley MCP

  • Create a video slideshow from a set of image URLs via chat.
  • Edit an existing project by giving a natural‑language prompt.
  • Automate video generation in backend systems using the REST API.
  • Integrate video editing into an AI assistant workflow.

常见问题

1

How does authentication work?

Clients authenticate each request. Use an API key from Settings → API Keys sent as a Bearer token, or let the client run an OAuth sign‑in flow.

2

What are the runtime requirements to self‑host?

Bun >= 1.1 (or Docker) and a Rendley account. The server holds no credentials; it talks to the hosted Rendley API and editor. Local mode needs Chrome (bundled or system) or a remote browser worker.

3

Where does video data live?

Media attachments must be public URLs – the editor imports them via the batch upload API. No local‑file uploads are accepted through MCP.

4

What transports are available?

The server supports MCP Streamable HTTP at `/mcp` and a plain REST endpoint at `/v1/agent` (asynchronous, pollable). A health check is at `/health`.

5

Are there any known limits?

Jobs run asynchronously; completed results are held in memory for 1 hour. A server restart drops all job state. The browser is single‑tenant per instance; concurrent jobs are handled via separate tabs.

评论

其他 分类下的更多 MCP 服务器