UGC Fans

Official26 tools

by ugcfans

Make ads, images and video from a URL; every paid generation is quoted in credits first

fans.ugc/make (MCP Server)

The fans.ugc/make MCP server generates ads, images, and video from a URL. It provides a workflow where each paid generation is quoted in credits first, indicating credit-based handling before generation occurs.

🛠️ Key Features

Create ads from a URL
Create images from a URL
Create video from a URL
Paid generations require a credits quote first

🚀 Use Cases

Generating visual/creative outputs (ads, images, video) sourced from a given URL
Managing paid generation by reviewing credit quotes before proceeding

⚡ Developer Benefits

Clear credit-first quoting behavior for paid runs
URL-based input for generating multiple media types

⚠️ Limitations

Only described as generating ads, images, and video from a URL; no other capabilities are specified

Captured live from the server via tools/list.

ugcfans_search_templates

Lists the ad templates, ad features and creation modes UGC Fans offers, each with its slug, name and a sentence on what it makes. Free, and needs no sign-in. A template slug goes into ugcfans_make_ad as template; a feature slug as feature.

Parameters1

query

string

optional

Words to look for in names and descriptions, such as "testimonial" or "product video". Leave out to list everything.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Words to look for in names and descriptions, such as \"testimonial\" or \"product video\". Leave out to list everything.",
      "maxLength": 200
    }
  },
  "required": [],
  "additionalProperties": false
}

ugcfans_get_account

Shows the signed-in account's credits left, credits granted and spent this period, when they expire, its plan and whether the account is admitted to UGC Fans. Free.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "required": [],
  "additionalProperties": false
}

ugcfans_capture_website

Opens a public web page in a sandboxed browser, records its text, pictures and layout, and returns a job whose result is a capture id. A capture is the raw material of ugcfans_make_launch_film and ugcfans_make_site_sting. Free of credits. Calling it confirms the person has the right to reuse the page's content in their own films. Only http and https pages on ports 80 and 443 can be captured.

Parameters2

url	string	required	The address of the page, starting with https:// or http://.
viewport	string	optional	desktop captures a 1280 by 900 window (the default); phone captures 390 by 844 at twice the density.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The address of the page, starting with https:// or http://.",
      "maxLength": 2048
    },
    "viewport": {
      "type": "string",
      "description": "desktop captures a 1280 by 900 window (the default); phone captures 390 by 844 at twice the density.",
      "enum": [
        "desktop",
        "phone"
      ]
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

ugcfans_get_capture

Reads a finished capture: the address it ended on, the parts of the page that can go into a film (node_id, role and the first words), and whether a launch film can be made from it. Free.

Parameters1

capture

string

required

The capture id from the finished ugcfans_capture_website job.

Raw schema

{
  "type": "object",
  "properties": {
    "capture": {
      "type": "string",
      "description": "The capture id from the finished ugcfans_capture_website job.",
      "maxLength": 128
    }
  },
  "required": [
    "capture"
  ],
  "additionalProperties": false
}

ugcfans_make_launch_film

Makes a 12-second launch film of the page's headline, button and picture from a finished capture, in the chosen frame, and returns a job. The result is an editable film; ugcfans_export_film renders it to MP4. Free of credits. A launch film has no text layers: its words are pictures of the page.

Parameters2

capture	string	required	The capture id.
aspect	string	required	The frame: 16:9 landscape, 9:16 vertical, 1:1 square.

Raw schema

{
  "type": "object",
  "properties": {
    "capture": {
      "type": "string",
      "description": "The capture id.",
      "maxLength": 128
    },
    "aspect": {
      "type": "string",
      "description": "The frame: 16:9 landscape, 9:16 vertical, 1:1 square.",
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ]
    }
  },
  "required": [
    "capture",
    "aspect"
  ],
  "additionalProperties": false
}

ugcfans_make_site_sting

Makes a 12-second, 8-scene film from the page parts you choose (node_ids from ugcfans_get_capture), in the chosen frame. Unlike a launch film its page text stays as editable text, so ugcfans_set_film_words can change it. Free of credits. Returns the film and its first revision at once.

Parameters4

capture	string	required	The capture id.
node_ids	array	required	The node_id of each part to include, from ugcfans_get_capture.
aspect	string	required	The frame: 16:9 landscape, 9:16 vertical, 1:1 square.
key_phrase	string	optional	A phrase of the chosen text to feature. It must appear in the chosen parts.

Raw schema

{
  "type": "object",
  "properties": {
    "capture": {
      "type": "string",
      "description": "The capture id.",
      "maxLength": 128
    },
    "node_ids": {
      "type": "array",
      "description": "The node_id of each part to include, from ugcfans_get_capture.",
      "items": {
        "type": "string",
        "description": "A node_id.",
        "maxLength": 200
      },
      "minItems": 1,
      "maxItems": 100
    },
    "aspect": {
      "type": "string",
      "description": "The frame: 16:9 landscape, 9:16 vertical, 1:1 square.",
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ]
    },
    "key_phrase": {
      "type": "string",
      "description": "A phrase of the chosen text to feature. It must appear in the chosen parts.",
      "maxLength": 200
    }
  },
  "required": [
    "capture",
    "node_ids",
    "aspect"
  ],
  "additionalProperties": false
}

ugcfans_ad_to_film

Makes an editable film from a finished video ad, so its captions and end card can be changed, and returns the film and its first revision. The ad must be finished, must not already be a film, must be a video and at most 96 MiB. Free of credits.

Parameters1

string

required

The ad id, from a finished ugcfans_make_ad job.

Raw schema

{
  "type": "object",
  "properties": {
    "ad": {
      "type": "string",
      "description": "The ad id, from a finished ugcfans_make_ad job.",
      "maxLength": 128
    }
  },
  "required": [
    "ad"
  ],
  "additionalProperties": false
}

ugcfans_set_film_words

Changes text in a film: every text layer whose words contain find gets replace, and the result is saved as a new revision; the earlier revision stays as it was. Films made by ugcfans_make_launch_film have no text layers, so nothing changes in them. Free of credits.

Parameters3

film	string	required	The film id.
revision	string	required	The revision to edit.
replacements	array	required	Pairs of words to find and what to put in their place, applied in order.

Raw schema

{
  "type": "object",
  "properties": {
    "film": {
      "type": "string",
      "description": "The film id.",
      "maxLength": 128
    },
    "revision": {
      "type": "string",
      "description": "The revision to edit.",
      "maxLength": 128
    },
    "replacements": {
      "type": "array",
      "description": "Pairs of words to find and what to put in their place, applied in order.",
      "items": {
        "type": "object",
        "properties": {
          "find": {
            "type": "string",
            "description": "The words to find.",
            "minLength": 1,
            "maxLength": 400
          },
          "replace": {
            "type": "string",
            "description": "The words to put in their place.",
            "maxLength": 400
          }
        },
        "required": [
          "find",
          "replace"
        ],
        "additionalProperties": false
      },
      "minItems": 1,
      "maxItems": 20
    }
  },
  "required": [
    "film",
    "revision",
    "replacements"
  ],
  "additionalProperties": false
}

ugcfans_export_film

Renders one revision of a film to an MP4 with a content credential, and returns a job; when it is done the result carries a link to the file. Free of credits. A film with an unresolved rendering requirement cannot be exported.

Parameters2

film	string	required	The film id.
revision	string	required	The revision to render.

Raw schema

{
  "type": "object",
  "properties": {
    "film": {
      "type": "string",
      "description": "The film id.",
      "maxLength": 128
    },
    "revision": {
      "type": "string",
      "description": "The revision to render.",
      "maxLength": 128
    }
  },
  "required": [
    "film",
    "revision"
  ],
  "additionalProperties": false
}

ugcfans_finish_clip

Runs up to 6 finishing operations in order on a clip of the library, each on the file the one before made: trim, reformat to another frame, burn in captions, overlay a brand logo, close with an end card, or mix in music. Returns the last job, whose result links the finished file. A call that runs past 4 minutes returns the job it is on and the operations still to run. Free of credits. The clip must already be in the library: upload footage at https://ugc.fans/library, then find its address with ugcfans_list_files. mix confirms the person may use the music file.

Parameters2

source	string	required	The clip's address in the library, out/...
operations	array	required	The operations, in order.

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "The clip's address in the library, out/...",
      "maxLength": 512
    },
    "operations": {
      "type": "array",
      "description": "The operations, in order.",
      "items": {
        "type": "object",
        "properties": {
          "op": {
            "type": "string",
            "description": "What to do.",
            "enum": [
              "trim",
              "reformat",
              "captions",
              "overlay",
              "end_card",
              "mix"
            ]
          },
          "start": {
            "type": "number",
            "description": "trim: where to start, in seconds (default 0).",
            "minimum": 0
          },
          "end": {
            "type": "number",
            "description": "trim: where to stop, in seconds.",
            "minimum": 0
          },
          "aspect_ratio": {
            "type": "string",
            "description": "reformat: the new frame.",
            "enum": [
              "9:16",
              "1:1",
              "16:9",
              "4:5"
            ]
          },
          "mode": {
            "type": "string",
            "description": "reformat: crop the picture, pad it, or follow the subject (default crop).",
            "enum": [
              "crop",
              "pad",
              "follow"
            ]
          },
          "transcript": {
            "type": "string",
            "description": "captions: the id of a transcript from ugcfans_transcribe.",
            "maxLength": 128
          },
          "cues": {
            "type": "array",
            "description": "captions: the lines to show, each with start and end seconds and its text.",
            "items": {
              "type": "object",
              "properties": {
                "start": {
                  "type": "number",
                  "description": "Seconds.",
                  "minimum": 0
                },
                "end": {
                  "type": "number",
                  "description": "Seconds.",
                  "minimum": 0
                },
                "text": {
                  "type": "string",
                  "description": "The line.",
                  "maxLength": 400
                }
              },
              "required": [
                "start",
                "end",
                "text"
              ],
              "additionalProperties": false
            },
            "maxItems": 2000
          },
          "brand": {
            "type": "string",
            "description": "overlay and end_card: the id of a saved brand; overlay puts its logo in the top-right corner, and end_card uses its colours and logo.",
            "maxLength": 128
          },
          "headline": {
            "type": "string",
            "description": "end_card: the closing headline.",
            "maxLength": 200
          },
          "subline": {
            "type": "string",
            "description": "end_card: a second line.",
            "maxLength": 200
          },
          "music": {
            "type": "string",
            "description": "mix: the address of the music file, out/..., which the person has the right to use.",
            "maxLength": 512
          }
        },
        "required": [
          "op"
        ],
        "additionalProperties": false
      },
      "minItems": 1,
      "maxItems": 6
    }
  },
  "required": [
    "source",
    "operations"
  ],
  "additionalProperties": false
}

ugcfans_transcribe

Writes out the words of an audio or video file in the library, up to 10 minutes long, with the built-in speech model, and returns a job; when it is done the result has the transcript id, its text, the language and the length. The transcript id feeds the captions operation of ugcfans_finish_clip. Free of credits. Upload footage at https://ugc.fans/library first, then find its address with ugcfans_list_files.

Parameters1

source

string

required

The file's address in the library, out/...

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "The file's address in the library, out/...",
      "maxLength": 512
    }
  },
  "required": [
    "source"
  ],
  "additionalProperties": false
}

ugcfans_list_files

Lists files in the account's library, newest first: the path of each (out/...), its size and when it changed. Pictures, video, audio and fonts only. Free. Footage is added at https://ugc.fans/library; the path is what the clip and transcript tools take as source.

Parameters2

prefix	string	optional	Only paths that start with this, such as out/api/images. The default is the whole library, out.
limit	integer	optional	How many files to list, newest first.

Raw schema

{
  "type": "object",
  "properties": {
    "prefix": {
      "type": "string",
      "description": "Only paths that start with this, such as out/api/images. The default is the whole library, out.",
      "maxLength": 512
    },
    "limit": {
      "type": "integer",
      "description": "How many files to list, newest first.",
      "minimum": 1,
      "maximum": 100
    }
  },
  "required": [],
  "additionalProperties": false
}

ugcfans_share_file

Makes a link that opens one file of the library for anyone who holds it, without signing in. A link lasts 6 hours; a showcase page, which carries the Made with UGC Fans badge, lasts 30 days. Free. Anyone with the link can see the file until it expires.

Parameters2

path	string	required	The file's address in the library, out/...
kind	string	optional	link opens the file itself (default); showcase is a page that shows it.

Raw schema

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "description": "The file's address in the library, out/...",
      "maxLength": 512
    },
    "kind": {
      "type": "string",
      "description": "link opens the file itself (default); showcase is a page that shows it.",
      "enum": [
        "link",
        "showcase"
      ]
    }
  },
  "required": [
    "path"
  ],
  "additionalProperties": false
}

ugcfans_get_job

Reads where a job stands: working, done with its files as links, failed with the reason, or cancelled. Free. Works for any job the account started.

Parameters1

job

string

required

The job id a tool returned, job_...

Raw schema

{
  "type": "object",
  "properties": {
    "job": {
      "type": "string",
      "description": "The job id a tool returned, job_...",
      "maxLength": 128
    }
  },
  "required": [
    "job"
  ],
  "additionalProperties": false
}

ugcfans_wait_job

Waits up to 45 seconds for a job to finish and reports where it stands, as ugcfans_get_job does. It returns as soon as the job ends. Free.

Parameters2

job	string	required	The job id a tool returned, job_...
seconds	integer	optional	How long to wait at most, up to 45 (default 45).

Raw schema

{
  "type": "object",
  "properties": {
    "job": {
      "type": "string",
      "description": "The job id a tool returned, job_...",
      "maxLength": 128
    },
    "seconds": {
      "type": "integer",
      "description": "How long to wait at most, up to 45 (default 45).",
      "minimum": 0,
      "maximum": 45
    }
  },
  "required": [
    "job"
  ],
  "additionalProperties": false
}

ugcfans_cancel_job

Stops a job that has not yet reached a provider; a cancelled job is not charged. A job that is already with a provider cannot be stopped and the call says so. Free.

Parameters1

job

string

required

The job id a tool returned, job_...

Raw schema

{
  "type": "object",
  "properties": {
    "job": {
      "type": "string",
      "description": "The job id a tool returned, job_...",
      "maxLength": 128
    }
  },
  "required": [
    "job"
  ],
  "additionalProperties": false
}

ugcfans_list_models

Lists what UGC Fans makes at each quality: stills, clips and talking clips, with the credits each costs per unit (an image, a clip) and whether a plan locks it. Free, and needs no sign-in. Signed out it is the whole price list; signed in it is what is on offer to this account, the model ids ugcfans_estimate and the make tools accept.

Parameters1

kind

string

optional

Only models of this kind.

Raw schema

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "description": "Only models of this kind.",
      "enum": [
        "image",
        "video",
        "avatar"
      ]
    }
  },
  "required": [],
  "additionalProperties": false
}

ugcfans_estimate

Prices a request without making it: the most it can cost in credits, the dollar figures behind it, any warnings, and a quote that is good for about 10 minutes. Free. The body takes the same fields as ugcfans_make_ad, ugcfans_make_image or ugcfans_make_video, without the quote; the make tool takes the quote back and refuses it if any field changed.

Parameters2

kind	string	required	What is being priced.
body	object	required	The request: the fields of the make tool for this kind, without quote.

Raw schema

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "description": "What is being priced.",
      "enum": [
        "ad",
        "image",
        "video"
      ]
    },
    "body": {
      "type": "object",
      "description": "The request: the fields of the make tool for this kind, without quote."
    }
  },
  "required": [
    "kind",
    "body"
  ],
  "additionalProperties": false
}

ugcfans_make_image

Makes a picture from a prompt, optionally following reference pictures, and returns a job; when it is done the result links the picture and a small one is shown inline. Spends the account's credits per picture (ugcfans_list_models gives each model's price). Call ugcfans_estimate first and pass its quote; without a quote this returns the cost and makes nothing.

Parameters7

model	string	required	The model id, from ugcfans_list_models.
prompt	string	required	What to draw, in words.
reference	array	optional	Pictures of the subject or style to follow: addresses of library files, out/...
n	integer	optional	How many pictures (default 1).
aspect_ratio	string	optional	The frame, such as 1:1, 9:16 or 16:9, when the model offers it.
resolution	string	optional	The resolution, such as 1K, when the model offers it.
quote	string	optional	The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "The model id, from ugcfans_list_models.",
      "maxLength": 200
    },
    "prompt": {
      "type": "string",
      "description": "What to draw, in words.",
      "maxLength": 4000
    },
    "reference": {
      "type": "array",
      "description": "Pictures of the subject or style to follow: addresses of library files, out/...",
      "items": {
        "type": "string",
        "description": "An address.",
        "maxLength": 512
      },
      "maxItems": 16
    },
    "n": {
      "type": "integer",
      "description": "How many pictures (default 1).",
      "minimum": 1,
      "maximum": 8
    },
    "aspect_ratio": {
      "type": "string",
      "description": "The frame, such as 1:1, 9:16 or 16:9, when the model offers it.",
      "maxLength": 20
    },
    "resolution": {
      "type": "string",
      "description": "The resolution, such as 1K, when the model offers it.",
      "maxLength": 20
    },
    "quote": {
      "type": "string",
      "description": "The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.",
      "maxLength": 4096
    }
  },
  "required": [
    "model",
    "prompt"
  ],
  "additionalProperties": false
}

ugcfans_make_video

Makes a video clip from a prompt, optionally beginning on a still, and returns a job; when it is done the result links the clip. Spends the account's credits per clip (ugcfans_list_models gives each model's price). Call ugcfans_estimate first and pass its quote; without a quote this returns the cost and makes nothing.

Parameters7

model	string	required	The model id, from ugcfans_list_models.
prompt	string	required	What happens, in words.
start_image	string	optional	A picture to begin on: the address of a library file, out/...
duration	integer	optional	The length in seconds, from the lengths the model offers.
aspect_ratio	string	optional	The frame, such as 9:16 or 16:9, when the model offers it.
resolution	string	optional	The resolution, such as 720p, when the model offers it.
quote	string	optional	The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "The model id, from ugcfans_list_models.",
      "maxLength": 200
    },
    "prompt": {
      "type": "string",
      "description": "What happens, in words.",
      "maxLength": 4000
    },
    "start_image": {
      "type": "string",
      "description": "A picture to begin on: the address of a library file, out/...",
      "maxLength": 512
    },
    "duration": {
      "type": "integer",
      "description": "The length in seconds, from the lengths the model offers.",
      "minimum": 1,
      "maximum": 60
    },
    "aspect_ratio": {
      "type": "string",
      "description": "The frame, such as 9:16 or 16:9, when the model offers it.",
      "maxLength": 20
    },
    "resolution": {
      "type": "string",
      "description": "The resolution, such as 720p, when the model offers it.",
      "maxLength": 20
    },
    "quote": {
      "type": "string",
      "description": "The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.",
      "maxLength": 4096
    }
  },
  "required": [
    "model",
    "prompt"
  ],
  "additionalProperties": false
}

ugcfans_make_ad

Makes a UGC-style ad from a product and a template or feature (testimonial, talking presenter, product video and others) and returns a job; when it is done the result lists the ad's files as links. Spends the account's credits; the cost depends on the feature and its length, so call ugcfans_estimate first and pass its quote. Without a quote this returns the cost and makes nothing. A presenter must be saved, have a portrait and, for a real person, recorded consent at https://ugc.fans/library.

Parameters11

feature	string	required	What kind of ad, a slug from ugcfans_search_templates such as testimonial, talking-presenter or product-video.
template	string	optional	A template slug from ugcfans_search_templates, which fills in the frame, length and shots.
product	any	optional	What is being sold: a sentence, or an object with its name, description and pictures.
person	string	optional	The presenter: the id of a saved person that has a portrait and, for a real person, recorded consent.
voice	string	optional	The voice: the id of a saved voice.
script	string	optional	A script already written, by its id from ugcfans_write_script.
page_url	string	optional	A web page to read the product from.
testimonial_basis	string	optional	Where a testimonial's words come from. verbatim and edited need reviews.
reviews	array	optional	Real customer reviews a testimonial rests on.
name	string	optional	A name for the ad.
quote	string	optional	The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.

Raw schema

{
  "type": "object",
  "properties": {
    "feature": {
      "type": "string",
      "description": "What kind of ad, a slug from ugcfans_search_templates such as testimonial, talking-presenter or product-video.",
      "maxLength": 64
    },
    "template": {
      "type": "string",
      "description": "A template slug from ugcfans_search_templates, which fills in the frame, length and shots.",
      "maxLength": 64
    },
    "product": {
      "description": "What is being sold: a sentence, or an object with its name, description and pictures.",
      "anyOf": [
        {
          "type": "string",
          "maxLength": 1200
        },
        {
          "type": "object",
          "properties": {
            "name": {
              "type": "string",
              "description": "The product's name.",
              "maxLength": 200
            },
            "description": {
              "type": "string",
              "description": "What it is and does.",
              "maxLength": 1000
            },
            "images": {
              "type": "array",
              "description": "Pictures of it: addresses of library files, out/...",
              "items": {
                "type": "string",
                "description": "An address.",
                "maxLength": 512
              },
              "maxItems": 12
            }
          },
          "required": [
            "name"
          ],
          "additionalProperties": false
        }
      ]
    },
    "person": {
      "type": "string",
      "description": "The presenter: the id of a saved person that has a portrait and, for a real person, recorded consent.",
      "maxLength": 128
    },
    "voice": {
      "type": "string",
      "description": "The voice: the id of a saved voice.",
      "maxLength": 128
    },
    "script": {
      "type": "string",
      "description": "A script already written, by its id from ugcfans_write_script.",
      "maxLength": 128
    },
    "page_url": {
      "type": "string",
      "description": "A web page to read the product from.",
      "maxLength": 2048
    },
    "testimonial_basis": {
      "type": "string",
      "description": "Where a testimonial's words come from. verbatim and edited need reviews.",
      "enum": [
        "verbatim",
        "edited",
        "composed"
      ]
    },
    "reviews": {
      "type": "array",
      "description": "Real customer reviews a testimonial rests on.",
      "items": {
        "type": "string",
        "description": "A review.",
        "maxLength": 800
      },
      "maxItems": 12
    },
    "name": {
      "type": "string",
      "description": "A name for the ad.",
      "maxLength": 80
    },
    "quote": {
      "type": "string",
      "description": "The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.",
      "maxLength": 4096
    }
  },
  "required": [
    "feature"
  ],
  "additionalProperties": false
}

ugcfans_write_script

Writes an ad script from a product or a web page, or, given a saved script, writes alternative opening hooks for it or translates it, and returns a job whose result holds the script. Spends a few of the account's credits. Give product or page_url to write a new script; give script with hooks (how many) or with translate_to (a language) to work on one.

Parameters12

product	string	optional	What is being sold, in a sentence or two.
page_url	string	optional	A web page to read the product from, instead of product.
audience	string	optional	Who the ad is for.
offer	string	optional	The offer or call to action.
points	array	optional	Points the script should make.
seconds	integer	optional	How long the ad runs, 5 to 120 (default 30).
angle	string	optional	The angle or hook to take.
language	string	optional	The language to write in (default English).
brand	string	optional	The id of a saved brand whose voice to follow.
script	string	optional	The id of a saved script to work on, from an earlier ugcfans_write_script.
hooks	integer	optional	With script: how many alternative openings to write.
translate_to	string	optional	With script: the language to translate it into.

Raw schema

{
  "type": "object",
  "properties": {
    "product": {
      "type": "string",
      "description": "What is being sold, in a sentence or two.",
      "maxLength": 1200
    },
    "page_url": {
      "type": "string",
      "description": "A web page to read the product from, instead of product.",
      "maxLength": 2048
    },
    "audience": {
      "type": "string",
      "description": "Who the ad is for.",
      "maxLength": 400
    },
    "offer": {
      "type": "string",
      "description": "The offer or call to action.",
      "maxLength": 300
    },
    "points": {
      "type": "array",
      "description": "Points the script should make.",
      "items": {
        "type": "string",
        "description": "A point.",
        "maxLength": 300
      },
      "maxItems": 12
    },
    "seconds": {
      "type": "integer",
      "description": "How long the ad runs, 5 to 120 (default 30).",
      "minimum": 5,
      "maximum": 120
    },
    "angle": {
      "type": "string",
      "description": "The angle or hook to take.",
      "maxLength": 200
    },
    "language": {
      "type": "string",
      "description": "The language to write in (default English).",
      "maxLength": 40
    },
    "brand": {
      "type": "string",
      "description": "The id of a saved brand whose voice to follow.",
      "maxLength": 128
    },
    "script": {
      "type": "string",
      "description": "The id of a saved script to work on, from an earlier ugcfans_write_script.",
      "maxLength": 128
    },
    "hooks": {
      "type": "integer",
      "description": "With script: how many alternative openings to write.",
      "minimum": 1,
      "maximum": 12
    },
    "translate_to": {
      "type": "string",
      "description": "With script: the language to translate it into.",
      "maxLength": 40
    }
  },
  "required": [],
  "additionalProperties": false
}

ugcfans_make_speech

Speaks a line or a saved script in a saved voice and returns a job whose result links the audio. Spends a few of the account's credits. Without a quote the call prices the line first and, when the pipeline can price it, makes it; a voice that cannot be priced ahead cannot be made here. A cloned voice needs its owner's recorded consent.

Parameters5

voice	string	required	The id of a saved voice, voice_...
text	string	optional	The words to speak.
script	string	optional	Or the id of a saved script to speak.
speed	number	optional	How fast, 0.5 to 1.5 (default 1).
quote	string	optional	A quote for exactly this line, when you hold one.

Raw schema

{
  "type": "object",
  "properties": {
    "voice": {
      "type": "string",
      "description": "The id of a saved voice, voice_...",
      "maxLength": 128
    },
    "text": {
      "type": "string",
      "description": "The words to speak.",
      "maxLength": 5000
    },
    "script": {
      "type": "string",
      "description": "Or the id of a saved script to speak.",
      "maxLength": 128
    },
    "speed": {
      "type": "number",
      "description": "How fast, 0.5 to 1.5 (default 1).",
      "minimum": 0.5,
      "maximum": 1.5
    },
    "quote": {
      "type": "string",
      "description": "A quote for exactly this line, when you hold one.",
      "maxLength": 4096
    }
  },
  "required": [
    "voice"
  ],
  "additionalProperties": false
}

ugcfans_make_performance

Puts a saved person on screen and returns a job: talking has them speak a line, motion has them move as a reference clip moves, swap puts them in place of the person in a clip, and product shows them holding a product (a picture). Spends the account's credits; a talking clip costs about what its avatar model costs (ugcfans_list_models, kind avatar). The person must be saved with a portrait and, if real, recorded consent at https://ugc.fans/library. motion and swap need rights_confirmed: true, given only after the person confirms they may use the source clip.

Parameters16

kind	string	required	What to make.
person	string	required	The id of the saved person.
speech	string	optional	talking: the id of a saved line to use as the audio.
script	string	optional	talking: the id of a saved script to speak.
text	string	optional	talking: words to speak.
voice	string	optional	talking, with script or text: the id of the saved voice to speak in.
image	string	optional	talking: which picture of the person to use, out/...
source	string	optional	motion and swap: the reference clip's address, out/...
rights_confirmed	boolean	optional	motion and swap: the person confirms they may use the source clip.
motion_from	string	optional	motion: follow the clip itself or its pose (default clip).
note	string	optional	swap: what to change, in words.
product	string	optional	product: the product's name.
product_images	array	optional	product: pictures of the product, out/...
brand	string	optional	product: the id of a saved brand whose kit holds the product pictures.
handling	string	optional	product: how the person has it.
setting	string	optional	motion and product: where it happens.

Raw schema

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "description": "What to make.",
      "enum": [
        "talking",
        "motion",
        "swap",
        "product"
      ]
    },
    "person": {
      "type": "string",
      "description": "The id of the saved person.",
      "maxLength": 128
    },
    "speech": {
      "type": "string",
      "description": "talking: the id of a saved line to use as the audio.",
      "maxLength": 128
    },
    "script": {
      "type": "string",
      "description": "talking: the id of a saved script to speak.",
      "maxLength": 128
    },
    "text": {
      "type": "string",
      "description": "talking: words to speak.",
      "maxLength": 5000
    },
    "voice": {
      "type": "string",
      "description": "talking, with script or text: the id of the saved voice to speak in.",
      "maxLength": 128
    },
    "image": {
      "type": "string",
      "description": "talking: which picture of the person to use, out/...",
      "maxLength": 512
    },
    "source": {
      "type": "string",
      "description": "motion and swap: the reference clip's address, out/...",
      "maxLength": 512
    },
    "rights_confirmed": {
      "type": "boolean",
      "description": "motion and swap: the person confirms they may use the source clip."
    },
    "motion_from": {
      "type": "string",
      "description": "motion: follow the clip itself or its pose (default clip).",
      "enum": [
        "clip",
        "pose"
      ]
    },
    "note": {
      "type": "string",
      "description": "swap: what to change, in words.",
      "maxLength": 400
    },
    "product": {
      "type": "string",
      "description": "product: the product's name.",
      "maxLength": 200
    },
    "product_images": {
      "type": "array",
      "description": "product: pictures of the product, out/...",
      "items": {
        "type": "string",
        "description": "An address.",
        "maxLength": 512
      },
      "maxItems": 3
    },
    "brand": {
      "type": "string",
      "description": "product: the id of a saved brand whose kit holds the product pictures.",
      "maxLength": 128
    },
    "handling": {
      "type": "string",
      "description": "product: how the person has it.",
      "enum": [
        "held",
        "worn",
        "used",
        "beside"
      ]
    },
    "setting": {
      "type": "string",
      "description": "motion and product: where it happens.",
      "maxLength": 300
    }
  },
  "required": [
    "kind",
    "person"
  ],
  "additionalProperties": false
}

ugcfans_read_reference

Reads a reference video of up to 3 minutes in the library and returns a job whose result is its breakdown: hook, structure, shots, pacing and look, with still frames, and none of its footage, sound or words. Spends a few of the account's credits. Using it confirms the person may study the file. Upload the video at https://ugc.fans/library first.

Parameters1

source

string

required

The video's address in the library, out/...

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "The video's address in the library, out/...",
      "maxLength": 512
    }
  },
  "required": [
    "source"
  ],
  "additionalProperties": false
}

ugcfans_save_asset

Saves a brand kit, a product, a generated presenter or a stock voice to the library for reuse in ads, and returns its id. Free. Only generated presenters (described in words, not a real person) and stock voices can be saved here: a real person's face or voice needs the consent the person records at https://ugc.fans/library. A new presenter has no picture until its portrait is drawn there.

Parameters16

kind	string	required	What to save.
name	string	required	Its name.
brand	string	optional	product: the id of the brand it belongs to.
product	string	optional	brand: what the brand sells.
description	string	optional	product: what it is. person: who the presenter is, drawn from these words.
url	string	optional	brand and product: their web address.
tone	string	optional	brand: its voice, such as warm and plain.
tagline	string	optional	brand: its tagline.
call_to_action	string	optional	brand: what an ad asks the viewer to do.
palette	object	optional
logo	string	optional	brand: the address of its logo, out/...
never	array	optional	brand: words and claims its ads never use.
images	array	optional	brand and product: addresses of product pictures, out/...
claims	array	optional	product: claims an ad may make about it.
provider_voice	string	optional	voice: the stock voice's name, from the speech models.
language	string	optional	voice: its language, as a tag such as en-US.

Raw schema

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "description": "What to save.",
      "enum": [
        "brand",
        "product",
        "person",
        "voice"
      ]
    },
    "name": {
      "type": "string",
      "description": "Its name.",
      "maxLength": 80
    },
    "brand": {
      "type": "string",
      "description": "product: the id of the brand it belongs to.",
      "maxLength": 128
    },
    "product": {
      "type": "string",
      "description": "brand: what the brand sells.",
      "maxLength": 600
    },
    "description": {
      "type": "string",
      "description": "product: what it is. person: who the presenter is, drawn from these words.",
      "maxLength": 1200
    },
    "url": {
      "type": "string",
      "description": "brand and product: their web address.",
      "maxLength": 300
    },
    "tone": {
      "type": "string",
      "description": "brand: its voice, such as warm and plain.",
      "maxLength": 400
    },
    "tagline": {
      "type": "string",
      "description": "brand: its tagline.",
      "maxLength": 160
    },
    "call_to_action": {
      "type": "string",
      "description": "brand: what an ad asks the viewer to do.",
      "maxLength": 80
    },
    "palette": {
      "type": "object",
      "properties": {
        "primary": {
          "type": "string",
          "description": "A colour, #RRGGBB.",
          "maxLength": 7
        },
        "secondary": {
          "type": "string",
          "description": "A colour, #RRGGBB.",
          "maxLength": 7
        },
        "text": {
          "type": "string",
          "description": "A colour, #RRGGBB.",
          "maxLength": 7
        },
        "background": {
          "type": "string",
          "description": "A colour, #RRGGBB.",
          "maxLength": 7
        }
      },
      "required": [],
      "additionalProperties": false
    },
    "logo": {
      "type": "string",
      "description": "brand: the address of its logo, out/...",
      "maxLength": 512
    },
    "never": {
      "type": "array",
      "description": "brand: words and claims its ads never use.",
      "items": {
        "type": "string",
        "description": "A word or claim.",
        "maxLength": 200
      },
      "maxItems": 50
    },
    "images": {
      "type": "array",
      "description": "brand and product: addresses of product pictures, out/...",
      "items": {
        "type": "string",
        "description": "An address.",
        "maxLength": 512
      },
      "maxItems": 12
    },
    "claims": {
      "type": "array",
      "description": "product: claims an ad may make about it.",
      "items": {
        "type": "string",
        "description": "A claim.",
        "maxLength": 200
      },
      "maxItems": 12
    },
    "provider_voice": {
      "type": "string",
      "description": "voice: the stock voice's name, from the speech models.",
      "maxLength": 200
    },
    "language": {
      "type": "string",
      "description": "voice: its language, as a tag such as en-US.",
      "maxLength": 35
    }
  },
  "required": [
    "kind",
    "name"
  ],
  "additionalProperties": false
}

README.md2 KBView on GitHub

UGC Fans

Make marketing media from inside your AI assistant. This plugin connects Claude Code, Codex, ChatGPT, Cursor, VS Code and Gemini CLI to the UGC Fans server at https://mcp.ugc.fans/mcp and adds four skills that tell the assistant how to use it: launch-film, ugc-ad, finish-clip and credits.

What it does

Photographs a website and makes a short launch film from it, in landscape, vertical or square.
Makes a UGC-style ad for a product from a template, with a script, a person and a voice.
Makes images and short video clips from a prompt.
Trims, captions, reformats, brands and transcribes footage you already have in your UGC Fans library, and shares finished files by link.

What it runs and what it sends

Nothing runs on your machine. The plugin is Markdown and JSON: one remote server entry and four skills. It has no scripts, hooks, commands or local servers, and it installs no packages.
Each tool call goes over HTTPS to https://mcp.ugc.fans with the arguments the assistant fills in: the website addresses you ask it to capture, the text for scripts and ads, file paths in your UGC Fans library and the options you choose. UGC Fans fetches and photographs the websites you name.
Searching the template catalogue and listing models work without an account. Everything else asks you to sign in at ugc.fans through the standard OAuth flow. The plugin holds no key, token or password in any file.

Credits

Generating images, video and ads spends credits from your UGC Fans account, and each one is quoted before anything is made. Website captures, launch films, clip finishing and transcripts run on UGC Fans' own compute and spend no credits. Plans and credits are described at https://ugc.fans/pricing.

Install

Claude Code: claude mcp add --transport http ugcfans https://mcp.ugc.fans/mcp, or the plugin from this repository's own marketplace: claude plugin marketplace add ugcfans/gpt-plugin then claude plugin install ugcfans@ugcfans.
Codex: codex mcp add ugcfans --url https://mcp.ugc.fans/mcp, then codex mcp login ugcfans.
Gemini CLI: gemini extensions install https://github.com/ugcfans/gpt-plugin.
Other clients: add https://mcp.ugc.fans/mcp as a remote Streamable HTTP server.

License

MIT. See LICENSE.

Source: https://github.com/ugcfans/gpt-plugin, published from the UGC Fans product tree; a change lands here with the ship that made it.

Install

Tools (26)

ugcfans_search_templatesugcfans_get_accountugcfans_capture_websiteugcfans_get_captureugcfans_make_launch_filmugcfans_make_site_stingugcfans_ad_to_filmugcfans_set_film_words

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.ugc.fans/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "make": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.ugc.fans/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

fans.ugc/make (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

ugcfans_search_templates

ugcfans_get_account

ugcfans_capture_website

ugcfans_get_capture

ugcfans_make_launch_film

ugcfans_make_site_sting

ugcfans_ad_to_film

ugcfans_set_film_words

ugcfans_export_film

ugcfans_finish_clip

ugcfans_transcribe

ugcfans_list_files

ugcfans_share_file

ugcfans_get_job

ugcfans_wait_job

ugcfans_cancel_job

ugcfans_list_models

ugcfans_estimate

ugcfans_make_image

ugcfans_make_video

ugcfans_make_ad

ugcfans_write_script

ugcfans_make_speech

ugcfans_make_performance

ugcfans_read_reference

ugcfans_save_asset

UGC Fans

What it does

What it runs and what it sends

Credits

Install

License

Install

Remote endpoint

Related servers