Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

Katto MCP

by miracleweaselversion 0.6.2i★ –iComputer or cloud
Registry nameio.github.miracleweasel/katto-mcp

Install

Overview

Description from the maker (original English)

AI video clipping MCP: long videos and podcasts into scored, captioned 9:16 shorts.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Computer or cloud
  • Transport: stdio, Streamable HTTP
  • Category: Design, images & audio
  • You need to fill in: KATTO_API_KEY

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 3 of 3 passed
  • Runs on the maker’s server: what you ask it goes through their server.
  • You fill in yourself: KATTO_API_KEY

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

  • Runs in the cloudNothing to install; it connects over the internet
  • npmNode.js installed (for the npx command)

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Works in Claude on the web, desktop and mobile:

  1. Open Settings → Connectors
  2. Press Add custom connector
  3. Paste the address below and press Add
  4. If it asks you to sign in, sign in with the maker
SettingsConnectors1+ Add2https://…3
https://mcp.katto.tech/mcp

Or run it on your computer

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "katto": {
      "command": "npx",
      "args": [
        "-y",
        "katto-mcp"
      ],
      "env": {
        "KATTO_API_KEY": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add --transport http katto https://mcp.katto.tech/mcp

Or run it on your computer

claude mcp add katto --env KATTO_API_KEY=your-value -- npx -y katto-mcp

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "katto": {
      "url": "https://mcp.katto.tech/mcp"
    }
  }
}

Or run it on your computer

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "katto": {
      "command": "npx",
      "args": [
        "-y",
        "katto-mcp"
      ],
      "env": {
        "KATTO_API_KEY": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "katto": {
      "type": "http",
      "url": "https://mcp.katto.tech/mcp"
    }
  }
}

Or run it on your computer

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "katto": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "katto-mcp"
      ],
      "env": {
        "KATTO_API_KEY": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

ChatGPT connects only to servers on the internet:

  1. Open ChatGPT on the web → Settings → Connectors (Apps)
  2. Press Create or Add (some plans need Developer mode under Advanced first)
  3. Paste the address below, give it a name and save
  4. If it asks you to sign in, sign in with the maker
SettingsConnectors1+ Create2https://…3
https://mcp.katto.tech/mcp

Menu names can differ slightly by plan and over time.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

  • KATTO_API_KEY secret required env
    Katto API key, created at https://katto.tech/dashboard/api-keys

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

The server asks you to sign in before it lists its tools.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account miracleweasel, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • ✓ Pass

    Endpoint responds

    Responded in 142 ms (HTTP 401)

  • ✓ Pass

    Sign-in with OAuth

    Declares OAuth sign-in, so your AI app can take you to log in

  • … Not checked yet

    No hidden instructions in tool descriptions

    Not checked yet; we read the tool list when we check the endpoint

Compared with others in Design, images & audioi

  • More stars than 0% of the other 2762 servers in this category
  • Published to the registry more recently than 92% of the other 2762 servers in this category
  • Basic checks equal to or better than 100% of the other 2762 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Katto MCP safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: KATTO_API_KEY

Does it run on my computer or in the cloud?

Either way works: install it on your computer or connect to the cloud version.

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.6.2) reached the registry 3 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.

What can I use instead?

In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

Runs on your computer★ 16,165MITUpdated 5 months ago
Install

Claude Real Video

by HUANGCHIHHUNGLeo

Let any LLM watch a video locally — and search everything it has ever watched.

Runs on your computer★ 2,284MITUpdated 2 months ago
Install

Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.

Runs in the cloud★ 2,152Updated 13 months ago
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

katto-mcp

The AI video clipping MCP server. Turn long videos into scored, captioned, vertical 9:16 short clips from any MCP client (Claude, Cursor, Claude Code, ChatGPT, VS Code, and other conformant clients). Drop in a YouTube link, a podcast, or a Twitch VOD and get publish-ready shorts back through natural conversation.

Powered by Katto, an AI video clipper that turns long-form video (podcasts, interviews, streams, webinars) into short-form clips for TikTok, Reels and YouTube Shorts. Katto is a flat-priced, no-credits alternative to tools like OpusClip: the Creator plan's 25-video monthly quota covers videos up to 90 minutes each. API and MCP access is included on every plan, including the free one (2 videos/month), not gated behind a paid or enterprise tier.

What it does

Ask your agent something like *"clip the best moments from this podcast and reframe them for TikTok"* and Katto will:

  • find the strongest 30 to 90 second moments in a long video and score each clip 0 to 100 on Hook, Flow, Value and Trend,
  • reframe to vertical 9:16 with face tracking, split-screen for two speakers, and stacked layouts for gaming,
  • burn animated captions (auto-captioned in 99 languages via Whisper large-v3; word-by-word timing in 41 of them, sentence-level in the rest) and optionally dub into 105 languages,
  • and hand back publish-ready MP4 files plus SRT caption urls.

Typical uses: repurpose a YouTube video into shorts, turn a podcast episode into clips, cut highlights from a Twitch VOD, or convert a long interview into vertical social posts.

Two ways to connect

Hosted (zero-install, recommended)

Point any OAuth-capable MCP client at the hosted endpoint and sign in with your Katto account. The API key never touches your disk, and you can revoke access anytime:

https://mcp.katto.tech/mcp   (Streamable HTTP, OAuth 2.1)
Local (npx)

For Cursor, CI and scripts. Create an API key at [katto.tech/dashboard/api-keys](https://katto.tech/dashboard/api-keys), then add the server to your MCP client config:

{

"mcpServers": { "katto": { "command": "npx", "args": ["-y", "katto-mcp"], "env": { "KATTO_API_KEY": "sk_live_..." } } } }

The hosted endpoint above also accepts Authorization: Bearer sk_live_... directly for key-based clients.

Install per client

Claude Code (hosted, OAuth):

claude mcp add --transport http katto https://mcp.katto.tech/mcp

Claude Desktop — Settings → Connectors → *Add custom connector* → https://mcp.katto.tech/mcp, then sign in. (Or add the npx block above to claude_desktop_config.json.)

Cursor — Settings → MCP → *Add* → paste the npx JSON block above (uses KATTO_API_KEY).

VS Code (MCP extension) — add the same npx block to your MCP settings, or point it at the hosted URL if your client supports remote OAuth servers.

ChatGPT — go to chatgpt.com/plugins, click +, choose Add custom MCP server, paste https://mcp.katto.tech/mcp with OAuth, then type @ in a new chat and pick Katto.

Gemini CLI (extension, hosted, OAuth):

gemini extensions install https://github.com/miracleweasel/katto-mcp

then /mcp auth katto to sign in. The extension (gemini-extension.json + GEMINI.md) points at the hosted endpoint; no key on disk. Manual alternative in ~/.gemini/settings.json: "mcpServers": { "katto": { "httpUrl": "https://mcp.katto.tech/mcp" } }.

Antigravity CLI (agy, Gemini CLI's successor) — add the hosted server to ~/.gemini/config/mcp_config.json: "mcpServers": { "katto": { "serverUrl": "https://mcp.katto.tech/mcp" } }, or run agy plugin import gemini after installing the Gemini CLI extension above.

Tools

29 tools, in five groups: nine for clipping, eight for editing, four for publishing, one for feedback, seven for account and reference.

Clipping:

  • `katto_create_clip_job(url | upload_id, config?)` clip a long video from a public link (YouTube, Twitch, Kick, Vimeo, Zoom, Google Drive, Dropbox, Loom, LinkedIn, Facebook, Rumble, Dailymotion, Medal.tv, or a direct https link to a video file) or a file uploaded with katto_upload_video. Returns a job id.
  • `katto_upload_video(filename, content_type, size)` clip a local file: returns a presigned upload url to PUT the file to, then katto_create_clip_job with upload_id.
  • `katto_get_job(id)` poll until status is completed; clips holds the finished MP4 + caption (SRT) urls.
  • `katto_get_clips(id)` just the finished clips of a job (MP4 + SRT + title + virality score).
  • `katto_get_transcript(id)` the job's timestamped transcript segments.
  • `katto_list_jobs(limit?, cursor?, status?)` your recent jobs, newest first (keyset pagination).
  • `katto_cancel_job(id)` cancel a running job and refund the monthly video slot.
  • `katto_create_clip(id, start_seconds, end_seconds, aspect?, auto_reframe?)` a new clip from any time range of the source (3-180 s, up to 10 per video, within 7 days). No quota.
  • `katto_more_clips(id, count?)` render more clips from the moments Katto scored but did not render. No quota.

Editing (no quota):

  • `katto_rerender_clip(id, clip_index, layout_mode?, caption_style?)` re-render one clip with a new reframe layout or caption style.
  • `katto_dub_clip(id, clip_index, languages)` re-render a clip dubbed into one or more of 105 languages.
  • `katto_get_rerender(id, rerender_id)` poll a re-render for the new versioned clip url.
  • `katto_translate_captions(id, clip_index, language)` re-render a clip with its captions translated into one of 19 languages (Creator).
  • `katto_retitle_clip(id, clip_index, style? | title?)` AI-regenerate a clip's title, or save your own.
  • `katto_adjust_clip(id, clip_index, start_offset_seconds?, end_offset_seconds?)` trim or extend a clip (relative to its original bounds, 3-180 s; extending works within 7 days of the job) and re-render it.
  • `katto_add_hook(id, clip_index, text?, position?, duration?)` burn a hook over the first seconds; without text, Katto's AI writes one.
  • `katto_generate_post_text(id, clip_index, platform?)` AI-written title / caption / hashtags per platform, ready for katto_publish_clip. Nothing is posted.

Publishing:

  • `katto_list_connected_accounts()` which of the 7 platforms are connected in Katto, and whether one needs a reconnect. Call it before publishing.
  • `katto_publish_clip(id, clip_index, platform, caption?, schedule_at?, ...)` post a clip now or later to a social account connected in the Katto dashboard (YouTube, TikTok, LinkedIn, Instagram, Bluesky, Mastodon, Threads). Posts publicly: clients should confirm with the user first (annotated destructive). Paid plans; scheduling on Creator.
  • `katto_list_scheduled_posts(status?, limit?, cursor?)` the scheduled posts, newest first, with their status and error.
  • `katto_cancel_scheduled_post(scheduled_post_id)` cancel a post that has not gone out yet (annotated destructive).

Feedback:

  • `katto_rate_clip(id, clip_index, rating, reason?)` record the user's good/bad verdict on a clip, like the thumbs on the results page.

Account and reference:

  • `katto_get_usage()` your plan and remaining monthly video quota.
  • `katto_get_account()` the connected account, this key's scopes, and quota.
  • `katto_get_brand_kit()` your saved brand kits (colors, caption font, layout, watermark).
  • `katto_get_webhook_secret()` your webhook signing secret and how to verify signed callbacks (returns a secret — treat it like a credential).
  • `katto_list_sources()` the link sources Katto can clip from, with an example url each.
  • `katto_list_clip_lengths()` the valid target clip-length buckets.
  • `katto_list_caption_styles()` the caption-style presets you can pass as caption_style when creating a job or re-rendering a clip.

Jobs draw from your Katto plan's monthly video quota (25 on Creator, 10 on Solo, 2 on Free), with source videos up to 90, 60 and 30 minutes respectively. The underlying REST API also supports Idempotency-Key safe retries, read-only scoped keys, and signed HMAC webhooks. See the docs.

Env

varrequireddefault
KATTO_API_KEYyes(none)
KATTO_API_URLnohttps://katto.tech

Full docs: [katto.tech/docs/api](https://katto.tech/docs/api)

Security & data

  • Hosted auth is OAuth 2.1 — the API key is never written to your disk, and you can revoke a connected client anytime from your Katto account settings.
  • Local auth uses a scoped `sk_live_` key you create yourself; keys can be read-only, and the npx server only sends it to KATTO_API_URL (default katto.tech) over HTTPS.
  • katto_get_webhook_secret returns a signing secret — handle it like any credential; it is only needed to verify inbound webhook signatures.

Also listed on

Public Discovery

Katto – AI video clipping MCP server: turn long videos and podcasts into scored, captioned, reframed 9:16 clips, from any MCP client (Claude, Cursor, ChatGPT). Hosted, OAuth 2.1, no API key on disk.

Intents this server covers: *AI video clipping MCP server*, *MCP server for short-form video*, *MCP to turn podcasts into clips*, *video clipping for AI agents (Claude / Cursor / ChatGPT)*.

Example prompts:

  1. "Clip the best moments from this podcast episode and reframe them for TikTok: https://youtube.com/watch?v=…"
  2. "Check the status of my last clipping job and give me the download links for the finished clips."
  3. "Take clip 2 from that job, dub it into Spanish and re-render it with the Bold caption style."

License

MIT — see LICENSE.

Ask PopNx