@metag/mcp
Generates video drafts from a prompt with a proprietary engine, then hands off to a human-editable timeline with tools for reshoots, takes, and media operations like image editing and speech synthesis.
README
@metag/mcp
把一句话变成一支片子，然后交给人去剪。
METAG 的 MCP 服务器。生成走我们自研的引擎（单镜约 3 秒画面，成本比调用同类 API 低一个数量级），剪辑走一个真实的时间线 —— 而这两件事之间是通的： agent 生成的每一镜都记得自己是怎么来的，人在时间线上右键就能把某一镜重拍掉。
装
现在就能用（包托管在我们自己的 CDN 上，不需要 npm 账号）：
# Claude Code
claude mcp add metag -- npx -y https://s3.metag.ai/metag/metag/cli/metag-mcp-latest.tgz
# 其它 MCP 客户端（Claude Desktop / Cursor / Codex …）
{
"mcpServers": {
"metag": {
"command": "npx",
"args": ["-y", "https://s3.metag.ai/metag/metag/cli/metag-mcp-latest.tgz"]
}
}
}
想钉死版本就把 latest 换成具体版本号，例如 metag-mcp-0.1.0.tgz ——
那个地址是不可变的，latest 会跟着更新走。
发布到 npm 之后会变成 npx -y @metag/mcp，上面的地址继续可用。
不需要先去弄 API key。 第一次调用时会弹浏览器登录，token 存在
~/.metag/token（0600），之后不再打扰你。
它给 agent 什么
| 工具 | 什么时候用 |
|---|---|
make_film |
用户要一支片子。0 credits —— 先出草案给人看，别直接花人家的钱 |
open_in_studio |
需要人的品味了（挑镜、调节奏、加自己的素材）。浏览器直接弹到那条时间线 |
reshoot_shot |
用户说"第三镜不对"。只重拍那一镜，别重生成整条片子把人剪好的东西扔掉 |
list_takes / promote_take |
看候选与质量分、定版。定版可逆，换下去的那条留着 |
get_recipe |
取逐镜提示词与旁白。和 Studio 导出的是同一份文档，可交给人也可喂回去重建 |
generate_video / job_status |
直接出片（立即扣费）与轮询 |
run_director / approve_run |
要先给人看报价时走这条 |
edit_image / synthesize_speech / account_balance |
改图、配音、查余额 |
完整参数见 https://metag.ai/docs。工具清单由服务端下发，这个包不维护副本 —— 所以服务端加了工具，你不用升级它。
环境变量
| 变量 | 作用 |
|---|---|
METAG_TOKEN |
直接给 token，跳过浏览器登录（CI 用） |
METAG_BROWSER=0 |
不弹浏览器。工具照样返回链接，能力不减 |
METAG_API |
网关地址，默认 https://api.metag.ai |
计费
草案免费。出片按镜计费，订阅用户用自研引擎不按条计费（有公平使用上限）。 生成失败自动退还。价格以 https://metag.ai/#pricing 为准。
许可
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.