Short Video Agent Kit
@davidmosiah
About Short Video Agent Kit
No overview available yet
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"short-video": {
"command": "npx",
"args": [
"-y",
"short-video-agent-kit"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Short Video Agent Kit?
A provider-neutral short-form AI video toolkit for agents. It gives Codex, Claude, Cursor, Hermes, OpenClaw and other MCP clients a single interface for building dry-run payloads and, when explicitly enabled, generating vertical video through Sora/OpenAI, Gemini Veo, xAI/Grok and Seedance/PiAPI-style providers. It is designed for anyone building agent workflows that need safe, credit-free prompt-to-video payload validation before optional paid generation.
How to use Short Video Agent Kit?
Install globally via npm (npm install -g short-video-agent-kit) or run directly with npx. Use the CLI commands doctor, generate, payload, manifest, privacy-audit to inspect providers, build plans, and generate video. Dry-run is the default; pass --live or set SHORT_VIDEO_DRY_RUN=false to enable paid provider calls. The package also ships as an MCP server (short-video-mcp) supporting stdio and HTTP transports. Configure provider API keys in a .env file.
Key features of Short Video Agent Kit
- Provider-neutral interface supporting OpenAI Sora, Gemini Veo, xAI/Grok, and Seedance.
- Dry-run by default — returns the exact payload plan without spending credits.
- API keys are detected but never returned by any tool.
- Paid generation requires explicit opt-in via
--liveor environment variable. - Built-in privacy audit tool for prompt and output boundaries.
- Outputs are written to user-controlled local paths.
Use cases of Short Video Agent Kit
- Building and validating video payloads across multiple AI video providers without spending credits.
- Comparing provider-specific parameter shapes for the same prompt before committing to one.
- Safely integrating short-form video generation into agent workflows with dry-run safety.
- Generating vertical short-form teasers and product videos through a single agent interface.
FAQ from Short Video Agent Kit
Which video providers are supported?
OpenAI Sora (openai_sora), Gemini Veo (gemini_veo), xAI/Grok (xai_grok), and Seedance/PiAPI (seedance_piapi).
Is an API key required to try it?
No. Generation is dry-run by default, so the kit returns the exact payload plan without making any provider call or spending credits.
How do I enable actual paid generation?
Pass the --live flag to the CLI, set live=true in the MCP tool call, or set the environment variable SHORT_VIDEO_DRY_RUN=false.
How are API keys handled?
Keys are detected from environment variables (or a .env file) and checked for readiness via short-video-agent-kit doctor, but they are never printed or returned by any tool.
What transports does the MCP server support?
The MCP server (short-video-mcp) uses stdio by default. Set SHORT_VIDEO_MCP_TRANSPORT=http to enable HTTP transport.
More AI & Agents MCP servers
LinkedIn MCP Server
stickerdanielOpen-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
Shell and Coding agent for Claude and other mcp clients
rusiaamanShell and coding agent on mcp clients
Perplexity Ask MCP Server
ppl-aiThe official MCP server implementation for the Perplexity API Platform
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Comments