riverside-mcp-server

riverside-mcp-server

MCP server for the Riverside Business API v3, enabling management of recordings, exports, webinars, timeline exports, and more through natural language in MCP clients.

Category
访问服务器

README

Riverside MCP Server

A local stdio MCP server for the Riverside Business API v3. It exposes every endpoint currently listed in Riverside's documentation as an MCP tool and includes a hand-authored OpenAPI 3.1 specification.

Works with Claude Desktop, Cursor, Codex, and other MCP clients that can launch a local stdio process.

Requirements

  • Node.js 20 or newer
  • A Riverside Business API key (the API is available only to select Riverside Business accounts)

Install

git clone YOUR_REPOSITORY_URL
cd riverside-mcp-server
npm install
npm run build

Do not place the API key in the repository. Supply it in your MCP client configuration.

Client configuration

Use an absolute path to dist/index.js.

{
  "mcpServers": {
    "riverside": {
      "command": "node",
      "args": ["/absolute/path/to/riverside-mcp-server/dist/index.js"],
      "env": {
        "RIVERSIDE_API_KEY": "YOUR_API_KEY",
        "RIVERSIDE_DOWNLOAD_DIR": "/absolute/path/to/downloads"
      }
    }
  }
}

This standard configuration shape is accepted directly by Claude Desktop and many other local clients. Cursor and Codex may store the same server definition in client-specific configuration files or expose an “Add MCP server” command.

Available tools

Tool Purpose
list_workspace List productions, studios, and projects
list_recordings / get_recording Find and inspect recordings
delete_recording Soft-delete a recording; requires confirm: true
list_exports / get_export Find and inspect exports
delete_export Permanently delete an export; requires confirm: true
download_file Download a recording track file
download_transcription Download SRT or TXT transcription
download_export Download exported audio/video
create_webinar_registrant Register a webinar participant
get_webinar_registrants Search and paginate webinar registrants
list_edits List edits/clips
create_timeline_export Queue Premiere, Final Cut, or Pro Tools timeline export
get_timeline_export Poll timeline export status
download_timeline Download a completed timeline ZIP

Downloads are written to RIVERSIDE_DOWNLOAD_DIR, or ./downloads if it is omitted. Riverside download redirects are followed automatically. Errors are returned to the MCP client as structured tool errors without exposing the API key.

OpenAPI

openapi.yaml describes all 16 documented v3 operations. It is community-authored from Riverside's public documentation and is not an official Riverside artifact.

Development and validation

npm test
npm run inspect

The server communicates only over stdout using MCP stdio. Diagnostics go to stderr so they do not corrupt protocol messages.

Documentation source

  • https://docs.riverside.fm/quickstart
  • https://docs.riverside.fm/llms.txt

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选