Autosophia Agent Video
Script in, finished 1080p narrated video out. Pay per call in USDC via x402.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"agent-video": {
"url": "https://mcp.autosophia.io/mcp"
}
}
}远程端点
https://mcp.autosophia.io/mcpstreamable-http它能做什么
工具清单
工具（8）
🟡submit_video_job(script, title, voice, subtitles, speed, ...)
Turn a script into a finished 1080p video — narrated, cut to matched stock footage, subtitles burned in, audio normalized to −14 LUFS. Returns a job id; poll get_job, then fetch_video. Use when you need a publishable video and have only text. $0.60 per video in USDC on Solana — no account, no API key, no human in the loop. script: narration body to speak (plain text) title: optional intro title shown for ~4s at the top voice: voice id from list_voices(), e.g. female_warm subtitles: burn-in subtitles (default true) speed: narration speed multiplier, e.g. 1.0 seed: stock-selection seed for reproducible visuals, e.g. 7
输入模式
{
"type": "object",
"properties": {
"script": {
"title": "Script",
"type": "string"
},
"title": {
"default": "",
"title": "Title",
"type": "string"
},
"voice": {
"default": "female_warm",
"title": "Voice",
"type": "string"
},
"subtitles": {
"default": true,
"title": "Subtitles",
"type": "boolean"
},
"speed": {
"default": 1,
"title": "Speed",
"type": "number"
},
"seed": {
"default": 7,
"title": "Seed",
"type": "integer"
}
},
"required": [
"script"
],
"title": "submit_video_jobArguments"
}🟢payment_info
How to pay, step by step. Read this if you got a 402 and are not sure what to do.
输入模式
{
"type": "object",
"properties": {},
"title": "payment_infoArguments"
}⚪service_info
Start here. What this server sells, what it will not do, and the exact limits.
输入模式
{
"type": "object",
"properties": {},
"title": "service_infoArguments"
}🟡list_voices
List narration voices you can pass to submit_video_job. Free.
输入模式
{
"type": "object",
"properties": {},
"title": "list_voicesArguments"
}🟡get_job(job_id)
Poll a video job until it is done. Free. Use after submit_video_job returns a job_id. job_id: id returned by submit_video_job, e.g. a1b2c3d4e5f6
输入模式
{
"type": "object",
"properties": {
"job_id": {
"title": "Job Id",
"type": "string"
}
},
"required": [
"job_id"
],
"title": "get_jobArguments"
}🟡fetch_video(job_id)
Fetch the finished video path and size once the job is done. Free. job_id: id returned by submit_video_job
输入模式
{
"type": "object",
"properties": {
"job_id": {
"title": "Job Id",
"type": "string"
}
},
"required": [
"job_id"
],
"title": "fetch_videoArguments"
}🟢list_jobs(limit)
List recent video jobs. Free. limit: max jobs to return, e.g. 20
输入模式
{
"type": "object",
"properties": {
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
}
},
"title": "list_jobsArguments"
}⚪request_capability(need, tried, would_pay_usd, contact)
Tell this server what you needed and could not get. Free — no payment required. Your input goes to the operator's queue and to a public board of unmet agent demand (contact details are never shared; entries are reviewed before publishing). Include what you would pay if you know.
输入模式
{
"type": "object",
"properties": {
"need": {
"title": "Need",
"type": "string"
},
"tried": {
"default": "",
"title": "Tried",
"type": "string"
},
"would_pay_usd": {
"default": 0,
"title": "Would Pay Usd",
"type": "number"
},
"contact": {
"default": "",
"title": "Contact",
"type": "string"
}
},
"required": [
"need"
],
"title": "request_capabilityArguments"
}社区
证据