Skip to content
MCP server

each::labs

Generate and edit images, video, audio and run workflows with each::labs from an AI chat

Install
Pricing
Paid
Platforms
Web, API
Runs
Remotely
Version
0.4.1
Listing updated
3 days ago

About each::labs

each::labs is a paid MCP server for design and media. It runs as a hosted remote server, so there is nothing to install locally.

The hosted each::labs server lets a chat client run each::labs models, trigger an organisation's saved workflows and use a Video API. Sign-in is OAuth, so no API key is pasted, and every run is billed to the organisation chosen on the consent page at the same prices as the REST API.

A large part of the tool list is video and audio editing: trimming without re-encoding, joining clips with a crossfade, speed changes from 0.25x to 4x, reframing to 9:16, 1:1, 4:5 or 16:9, LUT colour grading, burned-in or word-by-word captions, loudness normalisation, ducking music under speech, and silence and scene detection that return times instead of files. Long jobs return an id to poll with get_job or get_workflow_execution.

Scopes cover creating and reading predictions, running and reading workflows and uploading files. Tokens refresh while in use and expire after 30 days idle or 90 days overall. The README also describes a plugin for Claude, Codex and Grok Build that shows interactive cards in chat for uploading files or picking among results.

Install

Run in a terminal

claude mcp add --transport http mcp https://mcp.eachlabs.ai/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.eachlabs.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.eachlabs.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.eachlabs.ai/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.eachlabs.ai/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.eachlabs.ai/mcp"
    }
  }
}

Tools this server provides (17)

Taken from the project documentation; the running server may differ.

run_model
Run an each::labs model.
get_job
Check a running job by prediction id.
trigger_workflow
Start a workflow execution.
get_workflow_execution
Read a workflow execution by id.
trim
Cuts a clip by start time and length without re-encoding.
segment
Splits a video into equal-length parts.
concat
Joins 2 to 10 clips into one video.
crossfade
Joins two clips with a crossfade.
speed
Changes playback speed from 0.25x to 4x.
reframe
Changes aspect ratio for social formats.
captions
Burns subtitles into a video.
subtitle_compose
Creates animated word-by-word captions.
extract_audio
Extracts the audio track as mp3, wav or m4a.
audio_duck
Lowers background music while a voice speaks.
loudnorm
Normalises loudness to a target level.
silence_detect
Finds silent parts and returns their times.
scene_detect
Finds scene cuts and returns their times.

What it does

Model runs
Runs each::labs models for images, video, music and voice, with job polling for long runs.
Workflow triggers
Starts an organisation's workflows and reads execution results.
Video editing tools
Trim, concat, crossfade, speed, reverse, crop, scale, pad, rotate and reframe.
Captions and titles
Burns SRT, VTT or ASS subtitles and builds animated word-by-word captions.
Audio tools
Extract, replace, duck, master and normalise audio, and detect or remove silence.
Scoped OAuth
Five scopes limit what the client can run, read or upload.

Good for

  • Crop a clip to 9:16 for a story
  • Add burned-in captions to an interview
  • Lower background music under a voice-over
  • Find scene cuts or silent gaps in a recording
  • Run a team's saved product-clip workflow on a photo

Pricing

Paid

Runs bill to your each::labs organisation at REST API prices; rates not published here

Prices change. Check docs.eachlabs.ai before you buy.

each::labs FAQ

Do I need an API key?

No. You sign in with your each::labs account over OAuth.

Who gets billed?

The organisation chosen on the consent page, at the same prices as the REST API.

How long does sign-in last?

The token refreshes in use, and you sign in again after 30 days unused or 90 days after sign-in.

How are long jobs handled?

The call returns running, and you follow up with get_job or get_workflow_execution using the returned id.

Is each::labs free?

No. each::labs is a paid product.

How do I add each::labs to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.eachlabs.ai/mcp

What are the best alternatives to each::labs?

The closest alternatives to each::labs are HyperFrames by HeyGen, ffmpeg-skill, AvatarSay — Fictional Character & Talking Video MCP, ChartAnt and VfxSmith.

Alternatives to each::labs

  1. Hosted MCP connector for creating and rendering videos from HTML through AI chat

    • Remote
    • Freemium
    • 85.3K GitHub stars
    • Design and media
  2. ffmpeg-skill

    MCP server

    Local FFmpeg video and audio editing tools for coding agents over MCP

    Runs locally
    • Open source
    • 6.9K GitHub stars
    • Design and media
  3. ChartAnt

    MCP server

    Remote MCP server returning charts, maps and dashboards as hosted PNG links

    • 51 tools
    • Remote
    • Freemium
    • Design and media
  4. VfxSmith

    MCP server

    Search, generate, refine and export pixel art game effects from Claude Code or Codex

    Not checked yet
    • Remote
    • Freemium
    • Design and media
  5. CalderFlow

    MCP server

    Turn notes or specs into editable flowcharts, timelines and funnels from an AI assistant

    • 10 tools
    • Remote
    • Free
    • Design and media