Koskamo

Motion Text MCP

An official MCP server for Motion Text that allows AI agents to programmatically create lyric videos, kinetic typography, and photo stories. It supports creating drafts, applying visual presets, managing scenes and timed text, and queuing MP4 renders via the same JSON model used by the human editor.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Motion Text MCP logo, by Motion TextVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by Motion Text
MCP endpoint (Streamable HTTP)
https://motiontext.video/mcp
Vendor documentation

What its tools do

3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Can change data (1)

3 of 3 have a description · 3 of 3 declare behavior hints · 0 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to motiontext.video ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Create animated lyric videos with auto-synced text
  • Generate kinetic typography with timed effects
  • Queue server-side MP4 renders for high-resolution export
  • Manage scenes and visual presets programmatically

Source and maintenance

Vendor evidenceRegistry 1.0.0

Protocol and capabilities

Server
motion-text 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
3 advertised
Resources
1 advertised
Resource templates
0 advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  },
  "resources": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Motion Text builds real, editable video projects: image scenes with camera moves, timed text, overlays, audio, and panelled comic pages. You cannot see what you build, so check it: get_story_frames returns a labelled contact sheet from the same compositor as the MP4, free and unqueued, and validate_story_project reports what geometry alone can catch — overflowing text, colliding captions, a camera that pans off its own picture, a panel with nothing beneath it. Build, then look, then fix. A project that validates has not been checked. Start from a template when one fits. list_story_templates names them; each lays out a whole project deterministically, so the layout maths runs here rather than in your head. Templates create a new project by default and take dryRun. Timing before pacing. Anything that SPREADS content across the timeline uses the project's current duration as-is, so set the real length with set_story_duration first — a three-minute lyric paced into a default 12s timeline gives every line a fraction of a second. For panels and motion comics, establish a continuity bible before laying anything out: pick a master shot, note which side of frame each character occupies in it, and keep those sides on every later panel unless that panel declares reverseAngle. Express a change of scale as a change of PANEL, not as a moving crop — comics cut, they do not zoom. Pair an action with its consequence in reading order; on a cause/effect pair the cause must be the first panel, because left-to-right is what carries the causality. Everything you declare about a panel is stored as declared, never measured: that is what makes it checkable against the layout. Images must be public https:// URLs or asset urls returned by the image tools. A local file path is not reachable by the render server and renders as a plain background.

Tools

3 advertised

create_story_draft — Create story draft
Advertised by the server during the last successful anonymous check.

Create a complete, editable lyric-video or story-video draft and get back an edit link for the user. Prefer script mode (one beat per line) unless exact timings are known. Drafts expire after 30 days unless the user saves them. Most ads use one or two effects for the whole piece. fade, rise and pop read as professional; scatter, slam and glitch read as novelty and get tiring past a line or two. Vary the type SIZE and the vertical POSITION between lines rather than the effect — that is what makes a piece look composed rather than captioned.

create_story_draft input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "mood": {
      "enum": [
        "cinematic",
        "energetic",
        "intimate",
        "dark",
        "dreamy",
        "editorial"
      ],
      "type": "string"
    },
    "pace": {
      "enum": [
        "slow",
        "balanced",
        "fast"
      ],
      "type": "string"
    },
    "title": {
      "type": "string",
      "maxLength": 120
    },
    "format": {
      "enum": [
        "16:9",
        "9:16",
        "4:5",
        "1:1"
      ],
      "type": "string",
      "default": "16:9"
    },
    "scenes": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "start",
          "end"
        ],
        "properties": {
          "end": {
            "type": "number",
            "exclusiveMinimum": 0
          },
          "name": {
            "type": "string",
            "maxLength": 60
          },
          "start": {
            "type": "number",
            "minimum": 0
          },
          "background": {
            "type": "string",
            "maxLength": 300,
            "description": "CSS color or gradient only — images are added by the human in the editor."
          }
        }
      },
      "maxItems": 60
    },
    "script": {
      "type": "string",
      "maxLength": 8000,
      "description": "One story beat per line; the Director paces scenes and captions to match mood and pace. Provide script OR entries."
    },
    "entries": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "words",
          "start",
          "end"
        ],
        "properties": {
          "end": {
            "type": "number",
            "exclusiveMinimum": 0
          },
          "start": {
            "type": "number",
            "minimum": 0
          },
          "words": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1
          },
          "effect": {
            "enum": [
              "fade",
              "rise",
              "pop",
              "slide",
              "blur",
              "typewriter",
              "word-reveal",
              "karaoke",
              "cascade",
              "scatter",
              "beat",
              "breathe",
              "float",
              "slam",
              "glitch"
            ],
            "type": "string",
            "description": "How the line animates in. fade: The whole line fades from transparent to opaque without moving; on a word-timed line each word fades in separately over 0.3s at its own start. rise: The line fades in while travelling 18px (at 1080p, or an exact `distance`) from the `direction` side — up by default, so it starts below and settles upward. pop: The line scales up from 70% to full size while fading in, overshooting slightly past 100% before settling; set `fromScale` above 1 to settle down into place instead. slide: The line fades in while travelling 64px (at 1080p, or an exact `distance`) from the `direction` side — left by default, so it enters from the right. blur: The line resolves from a 14px defocus to sharp while fading in, then holds perfectly sharp and still; entrance only, never per-word. typewriter: Types the line one CHARACTER at a time at a constant rate, left to right, over `revealDuration` (default: the caption minus its hold). word-reveal: Reveals the line one whole WORD at a time with no motion — chunkier and more legible than typing; use `typewriter` for character-by-character. karaoke: The full line is visible from the first frame and the accent colour sweeps continuously through it, left to right, following measured word timings when the line has them. cascade: Words rise 18px and fade in one after another, 0.3s each and `stagger` (default 0.06s) apart, then hold still — a one-time ripple entrance, not a repeating wave. scatter: Breaks the line into separate words placed around the anchor at seeded offsets, tilts and sizes, each stamping in over 0.34s from 35% size; a lyric-card collage, best on 2–5 word lines. beat: The line snaps 5.5% larger on each detected music beat (9% on downbeats) and springs back within about a quarter second; with no beat grid it ticks steadily every 0.75s. breathe: The line oscillates smoothly and continuously between 97.5% and 102.5% scale, twice a second by default (`breathePeriod`), for as long as it is on screen. float: Each word drifts continuously in a slow figure-eight of about 4px vertically and 2px horizontally on a 2.2s loop, out of phase with its neighbours. slam: The line arrives at 190% size and accelerates down to full size in under 0.25s; set `fromScale` below 1 to punch UP from small instead, and `wobble` above 0 to add a decaying rattle. glitch: After the normal fade-in the line tears in 80ms bursts about a third of the time — red/cyan copies offset up to 6px plus a small jitter — for as long as it is on screen."
          }
        }
      },
      "maxItems": 300,
      "description": "Explicitly timed text, when you already know the timings."
    },
    "duration": {
      "type": "number",
      "maximum": 600,
      "minimum": 3
    },
    "presetId": {
      "enum": [
        "cinematic-noir",
        "neon-pulse",
        "paper-journal",
        "dream-haze",
        "horror-signal",
        "clean-editorial",
        "stage-spot",
        "tape-deck",
        "ice-cut",
        "clean-slate"
      ],
      "type": "string",
      "description": "Visual preset; see list_visual_presets."
    }
  }
}
create_story_draft annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
list_visual_presets — List visual presets
Advertised by the server during the last successful anonymous check.
Advertised read-only

Complete looks (treatment, typography, colors, motion) that can style a draft.

list_visual_presets input schema
{
  "type": "object",
  "properties": {}
}
list_visual_presets annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_spec — Get Motion Text spec
Advertised by the server during the last successful anonymous check.
Advertised read-only

Machine-readable capabilities, limits, draft schema, and integration endpoints.

get_spec input schema
{
  "type": "object",
  "properties": {}
}
get_spec annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

1 advertised

spec — Motion Text capability spec

Advertised by the server during the last successful anonymous check.

Capabilities, limits, and draft schema as JSON.

spec URI
motiontext://spec

MIME type: application/json

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
637 ms
95th percentile latency
637 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 637 ms · metadata changed · 3 tool(s), 1 resource(s), 0 resource template(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http motion-text-mcp https://motiontext.video/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add motion-text-mcp --url https://motiontext.video/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable motion-text-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "motion-text-mcp": {
      "url": "https://motiontext.video/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "motion-text-mcp": {
      "type": "streamableHttp",
      "url": "https://motiontext.video/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start motion-text-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "motion-text-mcp": {
      "type": "http",
      "url": "https://motiontext.video/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http motion-text-mcp https://motiontext.video/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://motiontext.video/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "motion-text-mcp": {
      "serverUrl": "https://motiontext.video/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Motion Text MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run Motion Text MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing