Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

WeCut

NPM · WECUT

Local video editing for AI agents: cut, caption, analyse, reuse viral formats. FFmpeg, no cloud.

Available components

71 Trust /100

Last scanned (4 hours ago)

Scores higher than 42% of npm servers

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 6 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability79
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1482 tokens (~114/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage93
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 79% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 24 Oct 26 +15
    • Malware scan: unverified → pass ▲ security
  • 23 Oct 26 56

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Oct 2026 · Analysed npm/wecut@0.1.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 6 packages
Packages resolved 6
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~1,243 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
wecut_analyze ~144

Measure a video that worked: shots and pace, cuts in the first 3 s, flashes, beat and tempo, pauses, a silent platform outro, and (with a transcript) words per minute and the hook's words. Returns a sheet of frames, one per shot, as an image: look at it for the headline card, text style, framing and captions. Use the result to pick or write a recipe.

NameTypeReqDescription
filestringyesVideo in the workspace.
framesinteger–Frames on the sheet (default 12).
transcriptstring–Word timings for it (.json, .srt, .vtt), optional.

No output schema declared.

No examples provided.

wecut_doctor ~42

Check that FFmpeg is installed and has what WeCut needs (libass, xfade, an H.264 encoder). Run once before the first render.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

wecut_example ~65

A complete working project to copy from: podcast-clip (cuts + karaoke captions + ducked music), slideshow (photos with motion and transitions) or product-promo (contain + blur, logo, text). Omit name to list them.

NameTypeReqDescription
namestring––

No output schema declared.

No examples provided.

wecut_list ~43

Names usable in a project: text styles, caption styles, fonts, transitions, filters, effects, motions, ratios and text animations.

NameTypeReqDescription
whatstring––

No output schema declared.

No examples provided.

wecut_preview ~135

Render a few still frames (540p JPEG) at chosen times of the finished video and return them as images, so you can check framing, text size and captions before rendering. Also saved under out/preview/.

NameTypeReqDescription
atarray–Times in seconds of the finished video. Default: 10%, 50% and 90%.
projectobject–The WeCut project (format "1") as a JSON object. wecut_schema has the full format; wecut_example shows working projects.
projectFilestring–Instead of project: path of a project .json file inside the workspace.

No output schema declared.

No examples provided.

wecut_probe ~51

Duration, width, height, fps, rotation and audio for video, image or audio files in the workspace. Use the durations for clip from/to.

NameTypeReqDescription
filesarrayyesPaths relative to the workspace.

No output schema declared.

No examples provided.

wecut_recipe_apply ~220

Turn a recipe plus new material into a project: clips (each with an optional role such as hook or body), words for the text slots, a transcript for captions, and music (replaces the recipe's own track; "none" drops it). Returns the project (saved with write); then wecut_preview and wecut_render it.

NameTypeReqDescription
captionSrcstring––
clipsarrayyes–
musicstring–Audio file, a video whose sound is used, or "none".
outputstring–Render target (.mp4 or .gif).
recipestring|objectyesBuilt-in name, workspace .json path, or a recipe object (wecut.recipe/1).
textsobject–Words per slot, e.g. {"headline": {"text": "...", "emphasis": ["key words"]}}.
transcriptstring–Word timings of captionSrc (or of the source used longest).
writestring–Save the project here (.json).

No output schema declared.

No examples provided.

wecut_recipe_from_project ~136

Make a reusable template from a finished project: sections, transitions, text slots (current words kept as defaults), caption style, effects, and its music as the default track.

NameTypeReqDescription
namestring––
projectobject–The WeCut project (format "1") as a JSON object. wecut_schema has the full format; wecut_example shows working projects.
projectFilestring–Instead of project: path of a project .json file inside the workspace.
writestring–Save it here, e.g. recipes/my-style.json, so wecut_recipe_list finds it.

No output schema declared.

No examples provided.

wecut_recipe_list ~53

Recipes are templates: the shape of an edit without its content (sections such as hook and body, text slots, caption and music style). Lists the built-in ones and the workspace's own (recipes/*.json).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

wecut_recipe_show ~46

A recipe in full, with the roles its clips can feed, its text slots, and its default music.

NameTypeReqDescription
namestringyesRecipe name or workspace .json path.

No output schema declared.

No examples provided.

wecut_render ~155

Render the project to output.file (MP4 or GIF) inside the workspace, overwriting an earlier render with the same name. The result is checked with ffprobe. Sends progress notifications when the call has a progressToken.

NameTypeReqDescription
outstring–Override output.file (must end in .mp4 or .gif).
presetstring–draft = 540p fast check, final = default, high = slower and sharper.
projectobject–The WeCut project (format "1") as a JSON object. wecut_schema has the full format; wecut_example shows working projects.
projectFilestring–Instead of project: path of a project .json file inside the workspace.

No output schema declared.

No examples provided.

wecut_schema ~45

The JSON Schema of the WeCut project format, with a description of every field. what=recipe gives the recipe (template) format instead.

NameTypeReqDescription
whatstring––

No output schema declared.

No examples provided.

wecut_validate ~108

Check a project against the media without rendering. Returns the finished duration and size, or every error with a JSON pointer (e.g. /clips/0/to) and a hint on how to fix it.

NameTypeReqDescription
projectobject–The WeCut project (format "1") as a JSON object. wecut_schema has the full format; wecut_example shows working projects.
projectFilestring–Instead of project: path of a project .json file inside the workspace.

No output schema declared.

No examples provided.

Install

How do I install the WeCut MCP server?

WeCut runs locally as an npm package, launched with npx -y wecut. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · wecut

# add to Claude Code
claude mcp add 13kailouis-stack-wecut -- npx -y wecut
Common questions

What is the WeCut MCP server?

WeCut is an MCP server listed in the public MCP registry as io.github.13kailouis-stack/wecut. Local video editing for AI agents: cut, caption, analyse, reuse viral formats. FFmpeg, no cloud. This page covers its npm package (wecut).

Is the WeCut MCP server safe to use?

WeCut scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the WeCut MCP server expose?

WeCut exposes 13 tools: wecut_doctor, wecut_probe, wecut_validate, wecut_preview, wecut_render, and 8 more. Their descriptions and schemas cost roughly 1,243 tokens of context every time the server is loaded.

Is the WeCut MCP server still maintained?

WeCut is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the WeCut MCP server under?

WeCut declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.