Mmcp.market

LeClap MCP server

by leclap.dev·dev.leclap/video·v0.3.4
No reviews yet

Compose and render video from one JSON template. Deterministic, runs locally, no generative model.

A91/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

24 stars52 downloads/wk

Reviews

Write one

Nobody has reviewed LeClap yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

LeClap tools (6)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • compose_video

    Render a video from an inline template descriptor (`template`). Supply user clips via userVideoPaths (absolute paths under the configured media dir) for each project_video section, optional form `fields`, and an optional `locale`. Renders in a forked worker and returns the output mp4 path plus duration/codec metadata.

  • get_template_schema

    Return the JSON Schema for a template descriptor plus a short authoring guide. Use this to understand the full set of fields when building or editing a template for compose_video.

  • ping

    Health check — returns a fixed readiness string.

  • probe_media

    Inspect a local media file (absolute path under the configured media dir) and return its duration, video/audio codecs, audio sample rate, and byte size. Probes via ffprobe directly so it never writes to stdout.

  • render_remotion_clip

    Render a composition from YOUR Remotion project to an mp4 (real motion graphics an FFmpeg filtergraph cannot express). Point it at your Remotion entry (`entry`, or a prebuilt `serveUrl`, or the configured --remotion-entry) and a `compositionId`, with optional `inputProps`. Returns the clip path; feed it to compose_video as a `project_video` clip (see sectionHint) so FFmpeg composites it in front o

  • validate_template

    Dry-run an inline `template` descriptor against the core schema WITHOUT rendering — returns instantly. Get back whether it is valid plus what compose_video will require: the project_video clip sections and the form fields. Use this to iterate on a descriptor in milliseconds before the slower compose_video render.

Public scan report

scanner v0.1.9 · 2026-09-21 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 26 days ago15/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the LeClap repository's README, as published. We do not edit it. Read it on GitHub

LeClap

Deterministic, on-device, agent-callable video — composed by prompt or by hand.

Describe a video in one JSON template — sections, filters, music, overlays — then render that same template on a phone (React Native, on-device) or in the browser (WebAssembly). No upload, no server, no generative model: the render is deterministic and reproducible, not sampled.

Quick start · Templates · Library API · Architecture · Docs

✨ What is LeClap?

One JSON template. It renders on Node, in the browser via WebAssembly, and natively on-device on React Native — same template, same pipeline, reproducible run after run on a given platform. No upload, no server, no generative model.

🎥 Demo

Two looks at LeClap — a finished clip rendered from a single JSON template, and the mobile app composing one fully on-device.

🎬 Template-driven render one JSON template → a finished clip · unmute for sound 📱 On-device on Android the app: capture → compose → render, on the phone

🤔 Why LeClap?

Generative tools can't reproduce a result twice. Cloud renderers can't run in your user's pocket. Remotion renders without a server, but needs a browser engine to do it — LeClap links FFmpeg into the app itself.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y @leclap/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add video -- npx -y @leclap/mcp
Add to Cursor

LeClap: common questions

Is LeClap MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the LeClap safety report
How do I install LeClap?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does LeClap need an API key?
No secret keys are declared. It reads 5 settings from the environment.
Is LeClap maintained?
The last commit was 26 days ago (2026-08-26). The latest release is v0.3.4.
What can I use instead of LeClap?
Servers from other publishers that do the same job: SkillTotal MCP server, Claude Real Video MCP server and IWE MCP server. Compare all LeClap alternatives.

Alternatives to LeClap

Same job from other publishers: the closest match first, then the best rated.

All LeClap alternatives →
  • SkillTotal
    Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.
    B
  • Claude Real Video
    Let any LLM watch a video locally — and search everything it has ever watched.
    A
  • IWE
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Agent-Native Assets
    Digital asset manager - upload, organize, search, and generate on-brand images and videos
    A
  • Orcareplay
    Read, replay and fork recorded coding-agent runs.
    A
LeClap vs SkillTotalLeClap vs Claude Real VideoLeClap vs IWE

More from leclap.dev →