MakeAIVideo

Official44 tools

by makeaivideo-ai · TypeScript

Create AI videos (voiceover, scenes, captions, music) and post them to TikTok, Reels, Shorts and X.

MCP Server: ai.makeaivideo/video-generator

The MCP server ai.makeaivideo/video-generator generates finished AI videos from a brief or a script. It supports adding voiceover, scenes, and captions, producing video output derived from the provided text inputs.

🛠️ Key Features

Generate finished AI videos
Input via brief or script
Voiceover generation
Scene creation
Captions

🚀 Use Cases

Turn a written brief into a complete video
Convert a script into a video with voiceover
Produce captioned videos with structured scenes

⚡ Developer Benefits

Uses text inputs (brief or script) as the source for video generation
Produces multiple components in one workflow (voiceover, scenes, captions)

⚠️ Limitations

Capabilities described are limited to generating videos from briefs or scripts; other inputs or integrations are not specified.

Topics

ai-agentsai-videoai-video-generatorchatgptclaudeclaude-codeclaude-desktopcursorgenerative-aiinstagram-reelsmakeaivideomcpmcp-servermodel-context-protocoltext-to-videotiktokvideo-generationyoutube-shortssocial-media-automationgemini-cli-extension

Declared in the repository manifest (tools.json). Not verified against a live endpoint.

create_explainer_video

Explainer video: Take one idea and make it land. We open on the question, explain the mechanism, and pay it off. Costs credits (use estimate_video_cost first). Returns a video id immediately; the render takes minutes - poll get_video_status.

Parameters4

topic	string	required	What do you want to explain?. One idea explains better than five. Narrow beats broad.
duration_seconds	number	optional	Target length in seconds. Options: 30, 45, 60, 90.
aspect_ratio	string	optional	Output aspect. Default 9:16.
idempotency_key	string	optional	Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying.

Raw schema

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "What do you want to explain?. One idea explains better than five. Narrow beats broad.",
      "maxLength": 1200
    },
    "duration_seconds": {
      "type": "number",
      "description": "Target length in seconds. Options: 30, 45, 60, 90."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ],
      "description": "Output aspect. Default 9:16."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying."
    }
  },
  "required": [
    "topic"
  ]
}

create_listicle_video

List video: Numbered tips, ranked picks, or things people get wrong. Each item gets its own scene. Costs credits (use estimate_video_cost first). Returns a video id immediately; the render takes minutes - poll get_video_status.

Parameters5

topic	string	required	What is the list about?
count	string	optional	How many items?. We will write fewer if the topic only supports fewer real items.
duration_seconds	number	optional	Target length in seconds. Options: 30, 45, 60, 90.
aspect_ratio	string	optional	Output aspect. Default 9:16.
idempotency_key	string	optional	Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying.

Raw schema

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "What is the list about?",
      "maxLength": 1200
    },
    "count": {
      "type": "string",
      "description": "How many items?. We will write fewer if the topic only supports fewer real items.",
      "maxLength": 2
    },
    "duration_seconds": {
      "type": "number",
      "description": "Target length in seconds. Options: 30, 45, 60, 90."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ],
      "description": "Output aspect. Default 9:16."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying."
    }
  },
  "required": [
    "topic"
  ]
}

create_story_video

Story video: Open inside the moment, escalate, reveal. Built for history, mysteries and true events. Costs credits (use estimate_video_cost first). Returns a video id immediately; the render takes minutes - poll get_video_status.

Parameters4

topic	string	required	What is the story?
duration_seconds	number	optional	Target length in seconds. Options: 30, 45, 60, 90.
aspect_ratio	string	optional	Output aspect. Default 9:16.
idempotency_key	string	optional	Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying.

Raw schema

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "What is the story?",
      "maxLength": 2000
    },
    "duration_seconds": {
      "type": "number",
      "description": "Target length in seconds. Options: 30, 45, 60, 90."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ],
      "description": "Output aspect. Default 9:16."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying."
    }
  },
  "required": [
    "topic"
  ]
}

create_ugc_video

UGC-style ad: Reads like a real recommendation, not an advert. Cold open, honest caveat, soft close. Costs credits (use estimate_video_cost first). Returns a video id immediately; the render takes minutes - poll get_video_status.

Parameters5

product	string	required	What are you promoting?
cta	string	optional	How should they close?
duration_seconds	number	optional	Target length in seconds. Options: 20, 30, 45.
aspect_ratio	string	optional	Output aspect. Default 9:16.
idempotency_key	string	optional	Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying.

Raw schema

{
  "type": "object",
  "properties": {
    "product": {
      "type": "string",
      "description": "What are you promoting?",
      "maxLength": 1200
    },
    "cta": {
      "type": "string",
      "description": "How should they close?",
      "maxLength": 80
    },
    "duration_seconds": {
      "type": "number",
      "description": "Target length in seconds. Options: 20, 30, 45."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ],
      "description": "Output aspect. Default 9:16."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying."
    }
  },
  "required": [
    "product"
  ]
}

create_demo_video

Product demo: Show the job getting done, step by step, and end on the result. Costs credits (use estimate_video_cost first). Returns a video id immediately; the render takes minutes - poll get_video_status.

Parameters5

product	string	required	What are you demonstrating?
cta	string	optional	Call to action
duration_seconds	number	optional	Target length in seconds. Options: 30, 45, 60.
aspect_ratio	string	optional	Output aspect. Default 16:9.
idempotency_key	string	optional	Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying.

Raw schema

{
  "type": "object",
  "properties": {
    "product": {
      "type": "string",
      "description": "What are you demonstrating?",
      "maxLength": 1200
    },
    "cta": {
      "type": "string",
      "description": "Call to action",
      "maxLength": 80
    },
    "duration_seconds": {
      "type": "number",
      "description": "Target length in seconds. Options: 30, 45, 60."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ],
      "description": "Output aspect. Default 16:9."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying."
    }
  },
  "required": [
    "product"
  ]
}

create_article_video

Article to video: Paste a blog post, newsletter or any writing. We select the spine and turn it into a short. Costs credits (use estimate_video_cost first). Returns a video id immediately; the render takes minutes - poll get_video_status.

Parameters4

source	string	required	Paste the article. We use only what is in your text. Nothing is invented or added.
duration_seconds	number	optional	Target length in seconds. Options: 30, 45, 60, 90.
aspect_ratio	string	optional	Output aspect. Default 9:16.
idempotency_key	string	optional	Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying.

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "Paste the article. We use only what is in your text. Nothing is invented or added.",
      "maxLength": 6000
    },
    "duration_seconds": {
      "type": "number",
      "description": "Target length in seconds. Options: 30, 45, 60, 90."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ],
      "description": "Output aspect. Default 9:16."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying."
    }
  },
  "required": [
    "source"
  ]
}

create_spokesperson_video

Spokesperson video: One presenter, straight to camera, for announcements and messages from you. Costs credits (use estimate_video_cost first). Returns a video id immediately; the render takes minutes - poll get_video_status.

Parameters5

topic	string	required	What is the message?
cta	string	optional	Closing line (optional)
duration_seconds	number	optional	Target length in seconds. Options: 20, 30, 45, 60.
aspect_ratio	string	optional	Output aspect. Default 9:16.
idempotency_key	string	optional	Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying.

Raw schema

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "What is the message?",
      "maxLength": 1500
    },
    "cta": {
      "type": "string",
      "description": "Closing line (optional)",
      "maxLength": 80
    },
    "duration_seconds": {
      "type": "number",
      "description": "Target length in seconds. Options: 20, 30, 45, 60."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ],
      "description": "Output aspect. Default 9:16."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional. Re-sending the same key returns the SAME video instead of creating (and charging for) a second one. Set it when retrying."
    }
  },
  "required": [
    "topic"
  ]
}

estimate_video_cost

Free. Quote the credit cost of a video before creating it. Same tools and arguments as the create_* tools.

Parameters2

tool	string	required	Which create tool the video would use.
duration_seconds	number	optional

Raw schema

{
  "type": "object",
  "properties": {
    "tool": {
      "type": "string",
      "enum": [
        "explainer",
        "listicle",
        "story",
        "ugc",
        "demo",
        "article",
        "spokesperson"
      ],
      "description": "Which create tool the video would use."
    },
    "duration_seconds": {
      "type": "number"
    }
  },
  "required": [
    "tool"
  ]
}

get_video_status

Check one video's progress. Returns status, a progress note, and download_url when ready. Respect poll_after_seconds between calls.

Parameters1

video_id

string

required

Public id, e.g. vid_abc123

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string",
      "description": "Public id, e.g. vid_abc123"
    }
  },
  "required": [
    "video_id"
  ]
}

list_my_videos

List this account's videos (id, title, status). Use it to recover a video id rather than guessing one.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

whoami

Free. Who this key belongs to: user, organization, plan, scopes and the live credit balance. Call first to confirm the connection works.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_credits

Free. The organization's credit balance: allowance, bonus, used (including in-flight reservations) and remaining.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_download_url

A signed URL for a finished video's MP4, valid 15 minutes. Only works once get_video_status reports ready.

Parameters1

video_id

string

required

Public id, e.g. vid_abc123

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string",
      "description": "Public id, e.g. vid_abc123"
    }
  },
  "required": [
    "video_id"
  ]
}

cancel_video

Stop a render that is still generating and release its reserved credits. Cannot undo a finished video.

Parameters1

video_id

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    }
  },
  "required": [
    "video_id"
  ]
}

list_voices

Free. Curated voices plus a filtered slice of the full catalog. Filters: gender, accent, age, use_case. Returns ids usable in future voice options.

Parameters4

gender	string	optional
accent	string	optional
age	string	optional
use_case	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "gender": {
      "type": "string"
    },
    "accent": {
      "type": "string"
    },
    "age": {
      "type": "string"
    },
    "use_case": {
      "type": "string"
    }
  }
}

list_characters

Free. Preset and workspace characters (id, name, style, image url).

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

list_templates

Free. The template library (id, title, which create tool it maps to).

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

write_script

Write the script only (no video, no render credits): title, hook and scenes with narration and visual directions. Give a topic, or a tool + fields from the create tools. Edit it, then create_video_from_script.

Parameters6

topic	string	optional	Free-text topic. Use this OR tool+fields.
tool	string	optional
fields	object	optional	The tool's brief fields by name.
target_duration	number	optional	Seconds, 10-1800.
mode	string	optional
language	string	optional	Language code or 'auto'.

Raw schema

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "Free-text topic. Use this OR tool+fields."
    },
    "tool": {
      "type": "string",
      "enum": [
        "explainer",
        "listicle",
        "story",
        "ugc",
        "demo",
        "article",
        "spokesperson"
      ]
    },
    "fields": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      },
      "description": "The tool's brief fields by name."
    },
    "target_duration": {
      "type": "number",
      "description": "Seconds, 10-1800."
    },
    "mode": {
      "type": "string",
      "enum": [
        "talking-head",
        "cinematic",
        "hybrid",
        "stock-narrated",
        "smart-mix"
      ]
    },
    "language": {
      "type": "string",
      "description": "Language code or 'auto'."
    }
  }
}

create_video_from_script

Render a video from a script you already have (from write_script, structure_text, or your own). Costs credits. Returns a video id; poll get_video_status.

Parameters9

script	object	required	The script object: title, hook, scenes[{scene_number, narration, visual_description, duration_seconds, scene_type?}], total_duration_seconds, hashtags?
mode	string	optional
character_id	number	optional	Optional: from list_characters.
voice_id	string	optional	Optional: from list_voices.
music_id	string	optional	Optional: from list_music.
aspect_ratio	string	optional
language	string	optional
start_generation	boolean	optional	Default true. false saves a draft; call generate_video later.
idempotency_key	string	optional	Same key = same video. Set it when retrying.

Raw schema

{
  "type": "object",
  "properties": {
    "script": {
      "type": "object",
      "description": "The script object: title, hook, scenes[{scene_number, narration, visual_description, duration_seconds, scene_type?}], total_duration_seconds, hashtags?"
    },
    "mode": {
      "type": "string",
      "enum": [
        "talking-head",
        "cinematic",
        "hybrid",
        "stock-narrated",
        "smart-mix"
      ]
    },
    "character_id": {
      "type": "number",
      "description": "Optional: from list_characters."
    },
    "voice_id": {
      "type": "string",
      "description": "Optional: from list_voices."
    },
    "music_id": {
      "type": "string",
      "description": "Optional: from list_music."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ]
    },
    "language": {
      "type": "string"
    },
    "start_generation": {
      "type": "boolean",
      "description": "Default true. false saves a draft; call generate_video later."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Same key = same video. Set it when retrying."
    }
  },
  "required": [
    "script"
  ]
}

structure_text

Turn prose or a hand-written script into our structured scene script (free apart from a small AI cost). Then create_video_from_script.

Parameters3

text	string	required
mode	string	optional
target_duration	number	optional

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "minLength": 20
    },
    "mode": {
      "type": "string"
    },
    "target_duration": {
      "type": "number"
    }
  },
  "required": [
    "text"
  ]
}

fetch_article

Fetch a public article's readable text so you can brief the article tool from a URL.

Parameters1

url

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string"
    }
  },
  "required": [
    "url"
  ]
}

update_video

Edit a video's title, topic, script or caption settings. Script edits apply on the next generate_video.

Parameters6

video_id	string	required
title	string	optional
topic	string	optional
script	object	optional
caption_style	string	optional
caption_alignment	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    },
    "title": {
      "type": "string"
    },
    "topic": {
      "type": "string"
    },
    "script": {
      "type": "object"
    },
    "caption_style": {
      "type": "string"
    },
    "caption_alignment": {
      "type": "string",
      "enum": [
        "top",
        "middle",
        "bottom"
      ]
    }
  },
  "required": [
    "video_id"
  ]
}

generate_video

Start or re-run generation for a draft, or after update_video edits. Costs credits.

Parameters1

video_id

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    }
  },
  "required": [
    "video_id"
  ]
}

regenerate_scene

Redo one scene's visuals, optionally with new narration. Costs credits.

Parameters3

video_id	string	required
scene_number	number	required
narration	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    },
    "scene_number": {
      "type": "number"
    },
    "narration": {
      "type": "string"
    }
  },
  "required": [
    "video_id",
    "scene_number"
  ]
}

regenerate_voice

Re-record the voiceover with another voice (from list_voices). Costs credits.

Parameters3

video_id	string	required
voice_id	string	required
voice_stability	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    },
    "voice_id": {
      "type": "string"
    },
    "voice_stability": {
      "type": "string",
      "enum": [
        "stable",
        "balanced",
        "expressive"
      ]
    }
  },
  "required": [
    "video_id",
    "voice_id"
  ]
}

export_video

Export (render) the video again after edits. Returns a render id; poll get_video_status.

Parameters1

video_id

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    }
  },
  "required": [
    "video_id"
  ]
}

get_captions

The finished video's captions as SRT or VTT text.

Parameters2

video_id	string	required
format	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    },
    "format": {
      "type": "string",
      "enum": [
        "srt",
        "vtt"
      ]
    }
  },
  "required": [
    "video_id"
  ]
}

create_share_link

A public, expiring link to the finished MP4 for people without an account (default 24h, max 7 days).

Parameters2

video_id	string	required
expires_in_seconds	number	optional

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    },
    "expires_in_seconds": {
      "type": "number"
    }
  },
  "required": [
    "video_id"
  ]
}

delete_video

Delete a video and its files. Irreversible. Confirm with the user first.

Parameters1

video_id

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string"
    }
  },
  "required": [
    "video_id"
  ]
}

generate_ideas

Scored video ideas for a niche and audience.

Parameters4

niche	string	required
audience	string	optional
tone	string	optional
count	number	optional

Raw schema

{
  "type": "object",
  "properties": {
    "niche": {
      "type": "string"
    },
    "audience": {
      "type": "string"
    },
    "tone": {
      "type": "string",
      "enum": [
        "educational",
        "entertaining",
        "inspirational",
        "humorous",
        "controversial"
      ]
    },
    "count": {
      "type": "number"
    }
  },
  "required": [
    "niche"
  ]
}

enhance_prompt

Rewrite a rough topic into a stronger brief before creating.

Parameters1

topic

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string"
    }
  },
  "required": [
    "topic"
  ]
}

generate_character_portraits

Generate 1-4 portrait candidates for a new character from a description. Costs credits. Returns r2_key values to pass to create_character.

Parameters4

prompt	string	required
style	string	required
count	number	optional
reference_image_urls	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string"
    },
    "style": {
      "type": "string"
    },
    "count": {
      "type": "number"
    },
    "reference_image_urls": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "prompt",
    "style"
  ]
}

generate_voice_previews

Candidate voices for a new character reading a sample line. Returns voice ids and preview temp keys for create_character.

Parameters2

sample_text	string	optional
gender_hint	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "sample_text": {
      "type": "string"
    },
    "gender_hint": {
      "type": "string",
      "enum": [
        "male",
        "female"
      ]
    }
  }
}

create_character

Save a character from a chosen portrait (r2_key) and voice preview (temp key + voice id).

Parameters6

name	string	required
style	string	required
description	string	optional
portrait_temp_key	string	required
voice_preview_temp_key	string	required
voice_id	string	required

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string"
    },
    "style": {
      "type": "string"
    },
    "description": {
      "type": "string"
    },
    "portrait_temp_key": {
      "type": "string"
    },
    "voice_preview_temp_key": {
      "type": "string"
    },
    "voice_id": {
      "type": "string"
    }
  },
  "required": [
    "name",
    "style",
    "portrait_temp_key",
    "voice_preview_temp_key",
    "voice_id"
  ]
}

generate_music

Generate a background track (15, 30 or 60 seconds) from a prompt and mood. Use the returned id as music_id when creating a video.

Parameters3

prompt	string	required
duration	number	optional
mood	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string"
    },
    "duration": {
      "type": "number",
      "enum": [
        15,
        30,
        60
      ]
    },
    "mood": {
      "type": "string"
    }
  },
  "required": [
    "prompt"
  ]
}

list_music

Free. Your generated background tracks.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

preview_voice

Hear a voice say your text (up to 500 characters). Returns a 1-hour audio URL.

Parameters2

voice_id	string	required
text	string	required

Raw schema

{
  "type": "object",
  "properties": {
    "voice_id": {
      "type": "string"
    },
    "text": {
      "type": "string"
    }
  },
  "required": [
    "voice_id",
    "text"
  ]
}

create_webhook

Receive video.created / video.ready / video.failed / character.created / post.published / post.partially_failed / post.failed at a public https URL instead of polling. The signing secret is returned once.

Parameters3

url	string	required
events	array	required
name	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string"
    },
    "events": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "video.created",
          "video.ready",
          "video.failed",
          "character.created",
          "post.published",
          "post.partially_failed",
          "post.failed"
        ]
      }
    },
    "name": {
      "type": "string"
    }
  },
  "required": [
    "url",
    "events"
  ]
}

list_webhooks

Free. Your webhooks and their delivery health.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

list_social_accounts

Free. The social accounts this workspace has connected (id acc_..., platform, name, can_post, needs_reconnection), the plan's account limit (limit, used), and every platform with how it connects. Platforms: TikTok, Instagram (posts as a Reel), YouTube (a 9:16 video posts as a Short, 16:9 as a regular video), Facebook (Pages only), LinkedIn, X (videos up to 140 seconds), Threads, Pinterest, Bluesky, Telegram and Discord. Call this before publish_video to get account ids; never guess them. An account with can_post false or needs_reconnection true must be reconnected by the user in the web app before posting.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_connect_link

Get a short-lived link that connects one social account. A PERSON must open the link in a browser and approve access; you cannot complete it yourself, so give the link to the user and ask them to open it. Then call list_social_accounts to see the new account. Works for tiktok, instagram (posts as a Reel; uses Instagram login, not Facebook), youtube (9:16 posts as a Short), facebook (Pages only), linkedin, x, threads and pinterest. Bluesky, Telegram and Discord connect with credentials in the web app only (Connections page): tell the user to connect them there. Refused when the plan's account limit is reached.

Parameters1

platform

string

required

The platform to connect.

Raw schema

{
  "type": "object",
  "properties": {
    "platform": {
      "type": "string",
      "enum": [
        "tiktok",
        "instagram",
        "youtube",
        "facebook",
        "linkedin",
        "threads",
        "pinterest"
      ],
      "description": "The platform to connect."
    }
  },
  "required": [
    "platform"
  ]
}

publish_video

Post a finished video (status ready) to one or more connected social accounts, now or at a scheduled time. This posts publicly on the user's real accounts: confirm the accounts and caption with the user first. Asynchronous: returns a post id (pub_...) at once; then poll get_publish_status until done is true (respect poll_after_seconds). Platforms: TikTok, Instagram (posts as a Reel), YouTube (a 9:16 video posts as a Short, 16:9 as a regular video), Facebook (Pages only), LinkedIn, X (videos up to 140 seconds), Threads, Pinterest, Bluesky, Telegram and Discord. Set idempotency_key when retrying so the video is not posted twice.

Parameters8

video_id	string	required	Public video id, e.g. vid_abc123. Must be ready.
account_ids	array	required	Account ids (acc_...) from list_social_accounts.
caption	string	required	Caption for every platform (hashtags included). Max 10000 characters.
caption_overrides	object	optional	Optional. A different caption per platform, keyed by platform id (e.g. {"linkedin": "..."}). Replaces caption on that platform only.
youtube_title	string	optional	Optional. YouTube title (max 100). Default: the video's own title.
scheduled_for	string	optional	Optional. ISO 8601 time to post at (for example 2026-10-01T15:00:00Z). Omit to post now. Posts go out within about 2 minutes of the time.
timezone	string	optional	Optional. IANA timezone for the schedule, e.g. Europe/London.
idempotency_key	string	optional	Optional. Same key within 24 hours returns the same post instead of posting again.

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string",
      "description": "Public video id, e.g. vid_abc123. Must be ready."
    },
    "account_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Account ids (acc_...) from list_social_accounts."
    },
    "caption": {
      "type": "string",
      "description": "Caption for every platform (hashtags included). Max 10000 characters."
    },
    "caption_overrides": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      },
      "description": "Optional. A different caption per platform, keyed by platform id (e.g. {\"linkedin\": \"...\"}). Replaces caption on that platform only."
    },
    "youtube_title": {
      "type": "string",
      "description": "Optional. YouTube title (max 100). Default: the video's own title."
    },
    "scheduled_for": {
      "type": "string",
      "description": "Optional. ISO 8601 time to post at (for example 2026-10-01T15:00:00Z). Omit to post now. Posts go out within about 2 minutes of the time."
    },
    "timezone": {
      "type": "string",
      "description": "Optional. IANA timezone for the schedule, e.g. Europe/London."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional. Same key within 24 hours returns the same post instead of posting again."
    }
  },
  "required": [
    "video_id",
    "account_ids",
    "caption"
  ]
}

get_publish_status

Status of one publish (post id pub_... from publish_video). status: preparing, importing, pending, scheduled, publishing, then published, partial or failed (done = true). Each destination has platform, status (pending, published, failed), url (the live post, when published) and error. Respect poll_after_seconds.

Parameters1

post_id

string

required

Post id, e.g. pub_abc123

Raw schema

{
  "type": "object",
  "properties": {
    "post_id": {
      "type": "string",
      "description": "Post id, e.g. pub_abc123"
    }
  },
  "required": [
    "post_id"
  ]
}

list_posts

Free. Past and scheduled publishes, newest first, with per-destination results and live post URLs. Filter by video_id. Paginate with cursor (next_cursor from the previous call).

Parameters3

video_id	string	optional	Optional. Only this video's posts.
limit	number	optional	1-100, default 20.
cursor	string	optional	next_cursor from the previous page.

Raw schema

{
  "type": "object",
  "properties": {
    "video_id": {
      "type": "string",
      "description": "Optional. Only this video's posts."
    },
    "limit": {
      "type": "number",
      "description": "1-100, default 20."
    },
    "cursor": {
      "type": "string",
      "description": "next_cursor from the previous page."
    }
  }
}

README.md11 KBView on GitHub

MakeAIVideo MCP Server

Let Claude, ChatGPT, Cursor and any MCP client make finished AI videos and post them. The MakeAIVideo MCP server gives your AI assistant 44 tools to write a script, generate a video with AI voiceover, AI or stock scenes, captions and music, hand back the MP4, and post it (now or scheduled) to your connected TikTok, Instagram Reels, YouTube Shorts, Facebook Pages, LinkedIn, X, Threads, Pinterest, Bluesky, Telegram and Discord accounts.

Ask your assistant things like:

"Make a 30-second explainer video about why octopuses have three hearts, vertical, and give me the MP4."
"Write a script for a UGC ad for my skincare product, then turn it into a video."
"Give me 10 video ideas for a personal finance channel and make the best one."
"When the video is ready, post it to my TikTok and YouTube tomorrow at 9am with a short caption."

Two ways to connect

1. Hosted server (recommended): `https://mcp.makeaivideo.ai`

Streamable HTTP with OAuth: add it as a custom connector and sign in, no key to copy.

Claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → https://mcp.makeaivideo.ai
ChatGPT: Settings → Connectors → Create → MCP server URL https://mcp.makeaivideo.ai

Claude Code:

bash

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

Cursor (~/.cursor/mcp.json) / VS Code (.vscode/mcp.json):

json

{ "mcpServers": { "makeaivideo": { "url": "https://mcp.makeaivideo.ai" } } }

Prefer an API key? Send Authorization: Bearer mav_... (create one in the developer settings).

2. Local stdio server (this package)

For clients that only run local commands. It bridges to the hosted server, so every tool stays in sync.

json

{
  "mcpServers": {
    "makeaivideo": {
      "command": "npx",
      "args": ["-y", "@makeaivideo/mcp"],
      "env": { "MAKEAIVIDEO_API_KEY": "mav_your_key" }
    }
  }
}

Works with Claude Desktop, Cursor, Windsurf, Cline, Zed, Continue and any stdio MCP client. Node 18+.

Or run it with Docker (the Dockerfile in this repo): docker build -t makeaivideo-mcp . && docker run -i --rm -e MAKEAIVIDEO_API_KEY=mav_your_key makeaivideo-mcp.

Without an API key the local server still starts and lists its tools (from the bundled tools.json snapshot), so clients can inspect it; every tool call then asks for a key. With a key, the tool list comes live from the hosted server.

Tools (44)

Area	Tools
Create videos	`create_explainer_video`, `create_listicle_video`, `create_story_video`, `create_ugc_video`, `create_demo_video`, `create_article_video`, `create_spokesperson_video`, `create_video_from_script`
Plan	`estimate_video_cost`, `write_script`, `structure_text`, `fetch_article`, `generate_ideas`, `enhance_prompt`
Track and deliver	`get_video_status`, `list_my_videos`, `get_download_url`, `get_captions`, `create_share_link`, `export_video`
Edit	`update_video`, `generate_video`, `regenerate_scene`, `regenerate_voice`, `cancel_video`, `delete_video`
Characters, voices, music	`list_characters`, `create_character`, `generate_character_portraits`, `generate_voice_previews`, `list_voices`, `preview_voice`, `generate_music`, `list_music`, `list_templates`
Post to social	`list_social_accounts`, `get_connect_link`, `publish_video`, `get_publish_status`, `list_posts`
Account and automation	`whoami`, `get_credits`, `create_webhook`, `list_webhooks`

Renders take minutes: the assistant creates the video, then polls get_video_status (it respects poll_after_seconds) and returns the download link.

publish_video posts a finished video to one or more connected accounts, now or at a scheduled time, with one caption or a caption per platform. Supported: TikTok, Instagram (as a Reel), YouTube (a 9:16 video as a Short, 16:9 as a regular video), Facebook (Pages only), LinkedIn, X (videos up to 140 seconds), Threads, Pinterest, Bluesky, Telegram and Discord.

A person must connect each account once: get_connect_link returns a short-lived link that the user opens in a browser to approve access (the assistant cannot complete it). Bluesky, Telegram and Discord connect in the web app. Then list_social_accounts returns the account ids, publish_video posts, and get_publish_status returns the live post URLs.

Full reference: makeaivideo.ai/docs/mcp.

Environment variables

Variable	Default	Purpose
`MAKEAIVIDEO_API_KEY`	(required)	Your `mav_` API key
`MAKEAIVIDEO_MCP_URL`	`https://mcp.makeaivideo.ai`	Override the remote endpoint

What you can make with MakeAIVideo

MakeAIVideo turns almost any starting point into a finished short-form video. Start from a single idea with prompt to video, or bring your own words with script to video and blog to video, which narrates a blog post you paste in. To teach a topic, AI explainer videos add voiceover, scenes, captions and music in one pass.

For a presenter on screen, AI talking avatar videos lip-sync a presenter you pick, or one made from your own reference photo, to a script. AI spokesperson videos suit corporate messaging you want to re-render when details change, and AI UGC video ads put an AI spokesperson on your ad script for Meta and TikTok. Character swap replaces the person in a video you upload while the motion and audio stay as filmed.

From a still image, image to video turns product shots, landscapes and album art into a moving clip, and animate a photo brings portraits, pets and old family photos to life.

Every video is sized for short-form platforms: use the TikTok video generator, the Instagram Reels generator or the AI YouTube Shorts generator, or run a faceless YouTube channel without filming. When a video is ready, auto-post to social media posts or schedules it to TikTok, Instagram, YouTube, Facebook Pages, LinkedIn, X, Threads, Pinterest, Bluesky, Telegram and Discord. Plans and credits are on the MakeAIVideo pricing page, and AI assistants connect through the MakeAIVideo MCP server setup guide.

From an AI assistant, the create_*_video tools cover explainer, listicle, story, UGC, demo, article and spokesperson videos plus your own scripts, and publish_video posts the result.

FAQ

What is the MakeAIVideo MCP server? A Model Context Protocol server that lets AI assistants create finished short-form AI videos with MakeAIVideo.

Does it cost anything? MakeAIVideo is a paid product with a 7-day trial (card required). The MCP server has no separate charge: videos use credits from your MakeAIVideo plan, and estimate_video_cost quotes before anything is spent. See pricing.

Can it post to social media? Yes. After you connect an account once, the assistant can post a finished video to TikTok, Instagram, YouTube, Facebook Pages, LinkedIn, X, Threads, Pinterest, Bluesky, Telegram or Discord, or schedule it.

Which AI assistants work? Anything that speaks MCP: Claude (web, desktop, Code), ChatGPT, Cursor, VS Code, Windsurf, Cline, Zed and more. See AI agents.

Is there a REST API too? Yes: API reference and the TypeScript SDK.

About MakeAIVideo

MakeAIVideo is an AI video generator that turns a brief, a prompt or your own script into a finished, captioned short-form video: script, AI voiceover, AI-generated or stock scenes, captions and music, exported as an MP4 ready for TikTok, Instagram Reels and YouTube Shorts.

For developers: developer hub, API reference, quickstart, authentication, webhooks, MCP server, AI agents, CLI
Compare: MakeAIVideo vs HeyGen, MakeAIVideo vs Synthesia
Free creator tools · Blog · Help · Contact

Links

Website: makeaivideo.ai
MCP setup guide: makeaivideo.ai/docs/mcp
Hosted MCP server: https://mcp.makeaivideo.ai
Developer hub: makeaivideo.ai/developers
API reference: makeaivideo.ai/docs/api · OpenAPI: app.makeaivideo.ai/api/v1/openapi.json
API keys: app.makeaivideo.ai/developers
npm: @makeaivideo/mcp · @makeaivideo/sdk · @makeaivideo/cli
GitHub: makeaivideo-ai/mcp · makeaivideo-ai/sdk · makeaivideo-ai/cli
Support: support@makeaivideo.ai

Package	What it is
`@makeaivideo/sdk`	TypeScript / JavaScript SDK for the REST API
`@makeaivideo/mcp`	MCP server for Claude, ChatGPT, Cursor and other AI assistants
`@makeaivideo/cli`	Command line tool: brief in, MP4 out

License

Install

Tools (44)

create_explainer_videocreate_listicle_videocreate_story_videocreate_ugc_videocreate_demo_videocreate_article_videocreate_spokesperson_videoestimate_video_cost

Configuration

Environment variables

MAKEAIVIDEO_API_KEYrequiredsecret

Your MakeAIVideo API key (mav_...), from https://app.makeaivideo.ai/developers

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "video-generator": {
      "command": "npx",
      "args": [
        "-y",
        "@makeaivideo/mcp@1.0.4"
      ],
      "env": {
        "MAKEAIVIDEO_API_KEY": "<YOUR_MAKEAIVIDEO_API_KEY>"
      }
    }
  }
}

MCP Server: ai.makeaivideo/video-generator

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

create_explainer_video

create_listicle_video

create_story_video

create_ugc_video

create_demo_video

create_article_video

create_spokesperson_video

estimate_video_cost

get_video_status

list_my_videos

whoami

get_credits

get_download_url

cancel_video

list_voices

list_characters

list_templates

write_script

create_video_from_script

structure_text

fetch_article

update_video

generate_video

regenerate_scene

regenerate_voice

export_video

get_captions

create_share_link

delete_video

generate_ideas

enhance_prompt

generate_character_portraits

generate_voice_previews

create_character

generate_music

list_music

preview_voice

create_webhook

list_webhooks

list_social_accounts

get_connect_link

publish_video

get_publish_status

list_posts

MakeAIVideo MCP Server

Two ways to connect

1. Hosted server (recommended): https://mcp.makeaivideo.ai

2. Local stdio server (this package)

Tools (44)

Posting to social accounts

Environment variables

What you can make with MakeAIVideo

FAQ

About MakeAIVideo

Links

Related packages

License

Install

Configuration

Related servers

1. Hosted server (recommended): `https://mcp.makeaivideo.ai`