Conversions across 221 color spaces, tested against cited sources: CSS strings, gamut, LUTs
AutoClip is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Clip long videos into short clips with covers and captions. Local CLI and MCP.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user autoclip-mcp '--' uvx autoclip-mcp
# 2 — ask your agent for something these tools do
# get_version, start_quick_output, get_quick_output_status and 11 more
AutoClip costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts AutoClip as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user autoclip-mcp '--' uvx autoclip-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take AUTOCLIP_API_KEY (Model API key. Optional when desktop settings already include one.) if you want to set it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
14 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
读取 AutoClip CLI / MCP 的版本号,核对同事的测试环境。
Takes no parameters.
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_status 查询。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source | string | yes | — |
| platforms | array | no | — |
| name | string | no | — |
| srt_path | string | no | — |
| instruction | string | no | — |
| browser | string | no | — |
| portrait_style | string | no | — |
| template | string | no | — |
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。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| export_kits | boolean | no | — |
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。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| video_path | string | yes | — |
| srt_path | string | no | — |
| name | string | no | — |
| category | string | no | — |
| min_score | number | no | — |
| provider | string | no | — |
| model | string | no | — |
| base_url | string | no | — |
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。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| video_path | string | yes | — |
| srt_path | string | no | — |
| name | string | no | — |
| category | string | no | — |
| min_score | number | no | — |
| provider | string | no | — |
| model | string | no | — |
| base_url | string | no | — |
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。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
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。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
列出最近的 AutoClip 项目(与桌面应用共用数据目录)。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
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。
Takes no parameters.
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。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| clip_id | string | yes | — |
| preset | string | no | — |
| subtitles | boolean | no | — |
| title_card | boolean | no | — |
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(环境变量 UPLOAD_POST_API_KEY,或 autoclip publish --api-key … --save)和…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| clip_id | string | yes | — |
| platforms | array | yes | — |
| user | string | no | — |
| preset | string | no | — |
| title | string | no | — |
| description | string | no | — |
| subtitles | boolean | no | — |
| title_card | boolean | no | — |
| scheduled_date | string | no | — |
| timezone | string | no | — |
| extra | object | no | — |
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。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request_id | string | yes | — |
| project_id | string | no | — |
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。
Takes no parameters.
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。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | no | — |
| model | string | no | — |
| base_url | string | no | — |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AutoClip or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
The source has registrations with unknown names: the tools registered at backend/mcp_server.py:451 get their names only at run time (a loop over a list the code builds, a name it computes), so they are not in this surface and were not analysed. To see them, scan the running server: --command "npx -y <package>".
backend/tests/test_vision_capability.py (2 KB) was not read: over the file-count budget.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_version | no tags | |
| start_quick_output | no tags | |
| get_quick_output_status | no tags | |
| start_clip_job | no tags | |
| get_job_status | no tags | |
| get_project | no tags | |
| list_projects | no tags | |
| list_providers | no tags | |
| get_publish_status | no tags | |
| list_publish_profiles | no tags | |
| check_environment | no tags | |
| clip_video | no tags | |
| export_clip | no tags | |
| publish_clip | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.5.7.post1. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish AutoClip can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.