AutoClip
2 Nov 2026
io.github.zhouxiaoka/autoclip-mcp
Clip long videos into short clips with covers and captions. Local CLI and MCP.
Install
uvx autoclip-mcp==1.5.7.post1
1 secret configuration field is declared. Names and values are omitted here.
Built for
Any MCP client. Works as a standard MCP server, so it can be added to any MCP client, including Claude, Cursor and Codex. Based on the listing description and package type. This is not a certification from those products.
Transports: stdio.
Links
Audit report
Audited by AddonAudit.
Sandbox handshake completed and the published checks passed.
Automated smoke test, not a security guarantee.
- Version
- 1.5.7.post1
- Audited
- 2 Nov 2026
- Package
- pypi autoclip-mcp
- Advisories
- 0 critical, 0 high, 0 medium, 0 low
- Time to ready
- 1877 ms
- Network
- Disabled
- Pass Version. Pinned pypi autoclip-mcp@1.5.7.post1
- Pass Known vulnerabilities. No critical, high, or medium advisories were returned.
- Pass License. MIT
- Pass Install scripts. No preinstall, install, postinstall, or prepare script.
- Pass Credential patterns. No credential patterns in the published artifact.
- Pass Package size. 12.9 MB
- Pass Maintainer activity. Active 7 days ago.
- Pass Sandbox. MCP handshake completed. 16 tools listed. Tool count measured offline in our sandbox; some servers load more tools when connected.
Tools
- get_version 读取 AutoClip CLI / MCP 的版本号,核对同事的测试环境。
- start_quick_output 一键出片:本地视频或 HTTPS 的 YouTube / B 站链接,按 platforms 自动制作视频、封面和发布文案。template 可选 editorial / street / classic,且只在 mcp_v2_tools 打开时接受;关闭时传了风格返回 disabled。返回的 template 是实际用的风格,requested_template 是请求值。共用桌面 AI 与片尾设置,立即返回 project_id;之后用 get_quick_output
- get_quick_output_status 查询一键出片状态。返回 progress、stage、eta、poll_after_sec,以及各平台的视频、封面和文案。完成后用 export_kits=true 获取发布包 ZIP 路径。查不到的任务是 unknown,进程不在是 interrupted。此工具不调用模型或启动制作。
- clip_video deprecated: 把一条本地视频切成高光片段(同步,耗时数分钟到数十分钟,期间会发进度)。返回切片列表(标题 / 起止时间 / 评分 / mp4 路径)与合集。provider 可选 dashscope / openai / gemini / deepseek / seed / kimi / glm / grok / infistar / api88 / ollama / lmstudio;不填用桌面应用里已配置的模型。
- start_clip_job deprecated: 后台开始出片,立刻返回 project_id;之后用 get_job_status 轮询进度和结果。适合客户端对单次工具调用有超时限制的情况。
- get_job_status deprecated: 查询 start_clip_job 开始的任务。返回 progress、stage、eta、poll_after_sec。没有记录是 unknown,工作进程不在是 interrupted,不会把查不到的项目报成 completed。
- get_project 读取一个已处理项目的切片(标题 / 时间 / 评分 / 文件)、合集与输出目录。
- list_projects 列出最近的 AutoClip 项目(与桌面应用共用数据目录)。
- list_providers 可用的模型提供商与本地预设(ollama / lmstudio 的默认地址与模型),以及当前正在用的配置。
- export_clip deprecated: 把一条已切好的片段渲成可直接发布的成片:9:16(抖音/小红书/Shorts)、烧字幕、标题卡。preset: douyin / xiaohongshu / shorts / bilibili / original。返回成片路径;同参数再导会走缓存。
- publish_clip deprecated: 把一条切片经 Upload-Post 发到海外平台(tiktok / instagram / youtube / facebook / linkedin / x / threads / pinterest / bluesky …),一次可发多个平台。内部先按预设渲成片(竖屏平台默认 shorts 9:16),再异步提交;返回 request_id,用 get_publish_status 查各平台结果。需要先配置 Upload-Post API Key
- get_publish_status deprecated: 查询 publish_clip 的结果:status(pending / processing / completed / failed)与每个平台的 success / url / error。processing 时每 10 秒查一次即可。
- list_publish_profiles deprecated: Upload-Post API Key 下的 profile(user)列表及各自已连接的平台;用户不知道该填哪个 user 时先调这个。同时返回当前配置是否就绪。
- check_environment 体检:ffmpeg、Whisper 运行时、模型连接是否就绪。出片前先调一次能少踩坑。
- cancel_job 取消一条仍在进行的出片或切片任务,停掉它的 ffmpeg。不删除已写出的成片。查不到返回 unknown。
- list_styles 列出剪辑风格 id:editorial(杂志风)、street(街头快剪)、classic(经典)。传给 start_quick_output 的 template 或 CLI 的 --template。
Metadata checks
- Repository activity: Active in the last 180 days
- License: Recognized SPDX id
- Metadata quality: High
Score 100 uses public metadata only. It is separate from the audit tier. Payment never changes a score. How listings are checked.
Audited by AddonAudit
Free to use on this listing. The mark links back to this page and does not change the score or the tier.
Light
[](https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/)
<a href="https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/"><img alt="Audited by AddonAudit" src="https://addonaudit.com/badges/audited.svg" width="168" height="20"></a>
Dark
[](https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/)
<a href="https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/"><img alt="Audited by AddonAudit" src="https://addonaudit.com/badges/audited-dark.svg" width="168" height="20"></a>
Seal, light
[](https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/)
<a href="https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/"><img alt="Audited by AddonAudit" src="https://addonaudit.com/badges/audited-seal.svg" width="240" height="240"></a>
Seal, dark
[](https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/)
<a href="https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/"><img alt="Audited by AddonAudit" src="https://addonaudit.com/badges/audited-seal-dark.svg" width="240" height="240"></a>
Self-hosted version
A remote image can be changed by whoever hosts it. To keep the badge fixed, download the SVG and commit it to your own repo, for example as .github/addonaudit-badge.svg. The snippet below uses that local file and links to this page.
Download light SVG · Download dark SVG
[](https://addonaudit.com/addon/io-github-zhouxiaoka-autoclip-mcp/)
Get your add-on audited
Request a free audit of a public MCP server or AI coding add-on. A request does not buy a listing, a tier, or a score change.
Data notes
- Tool count is not part of this registry record, so it is blank.