flo-plugin

flo-plugin

Integrates Flo's AI-powered media automation into Claude, enabling tasks like quality control, content moderation, delivery validation, and asset search via slash commands and MCP tools.

Category
访问服务器

README

Flo Plugin for Claude

The official Flomenco plugin for Claude. Brings Flo's AI-powered media automation directly into Claude Code via slash commands, and connects Claude Desktop to the Flo platform via MCP.


Quick start

1. Get your OAuth client ID

Sign in to floapp.co, go to Settings → API, and copy your OAuth client ID.

2. Add it to your shell profile

# ~/.zshrc or ~/.bashrc
export FLO_OAUTH_CLIENT_ID=<your-client-id>

Reload your shell:

source ~/.zshrc

3. Install the plugin

claude plugin install Flomenco-Inc/flo-plugin

4. Authenticate

Ask Claude to run flo_auth_login — it opens a browser window, completes the OAuth flow, and caches your token locally. You only need to do this once (or when your token expires).


Commands

Command Description
/flo-qc QC a media asset — logo consistency, spec compliance, timecode issues
/flo-moderate Content moderation against a target rating and platform
/flo-deliver Validate a media asset against platform delivery specs
/flo-search Search for assets in your Flo library
/flo-query Filename-first asset lookup
/flo-analyze Analyze a media asset directly
/flo-config Show current auth and config status

MCP tools

The plugin also exposes lower-level MCP tools for use in any MCP-capable client (Claude Desktop, Claude Code, etc.):

Tool Description
flo_auth_login Start OAuth login (browser PKCE flow)
flo_auth_status Show current auth state and token info
flo_auth_logout Clear cached token
flo_auth_setup_help Show where to find your client ID
flo_search Search the Flo asset library
flo_query Filename-first asset lookup
flo_analyze Analyze a media asset
flo_qc_logo Run logo QC against a reference asset
flo_skill_routing List available actions for an asset
flo_plugin_healthcheck Check auth and connectivity
flo_happy_path_run End-to-end validation in one call
flo_command Run a raw /flo:* command (escape hatch)

Claude Desktop installation

Run the install script (requires AWS credentials with Cognito read access):

npx @flomenco/claude-plugin-mcp install:claude-desktop

Or clone the repo and run:

node tools/install-claude-desktop.js

Then fully quit and relaunch Claude Desktop.


Troubleshooting

flo_auth_login fails with "Invalid URL" Your FLO_OAUTH_CLIENT_ID env var is not set. Go to floapp.co/settings/api to get your client ID, add export FLO_OAUTH_CLIENT_ID=<id> to your shell profile, reload, and reinstall the plugin.

flo_plugin_healthcheck returns unreachable Check that you have network access to plugin.floapp.co. If you're on a VPN, try disconnecting.

Commands not appearing after install Restart Claude Code, or run /reload-plugins.

Token expired Ask Claude to run flo_auth_logout followed by flo_auth_login.


Contributing

See CONTRIBUTING.md for how to add new tools or commands.

License

MIT — see LICENSE.

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