ClipUGC

Create an AI influencer

create_character

Optionally from a reference photo of the face (photo_file, photo_upload or photo_url). Create a new AI influencer from a plain description and generate the first look (2 credits, confirm with get_credits). Be specific: nationality, age (18 or older), hair, eyes, style, and a realism anchor such as "natural skin texture". Private by default; set public=true to add it to the cast anyone can use. make_video=true also stages the first 5 second clip (7 more credits) that starts on its own when the look is done. Returns the character, first_look_id and, with make_video, first_clip_id. Poll list_images until the look is completed.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	The influencer name. Optional; one is made up otherwise.
`hints`	No	Answers from a short interview; a description in the shape that works is composed from them when no description is given.
`scene`	No	Optional scene or pose for the first look, up to 600 characters.
`public`	No	Add to the public cast. Default false (private).
`photo_url`	No	An https link to a photo (png, jpg or webp, up to 8 MB) A reference photo the face is built from; the description still says who the influencer is.
`make_video`	No	Also stage the first 5 second clip (7 credits). Default false.
`photo_file`	No	A file the user attached to the chat, when the client supports that: a photo (png, jpg or webp, up to 8 MB) A reference photo the face is built from; the description still says who the influencer is.
`description`	No	Plain-words description of the person, 10 to 1000 characters (suggest_influencers gives ready ones). Optional when hints are given.
`photo_upload`	No	An upload id from list_uploads (the user dropped the file on the upload page from request_upload): a photo (png, jpg or webp, up to 8 MB) A reference photo the face is built from; the description still says who the influencer is.
`motion_prompt`	No	What happens in that first clip; needs make_video. Silent reactions work best: mouth closed, no talking.

Output Schema

TableJSON Schema

Name	Required	Description
`next`	Yes
`character`	Yes
`first_clip_id`	No	Only when make_video was true.
`first_look_id`	No	The first photo, generating.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 4, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only say it is a non-destructive write; the description adds the costly details an agent actually needs: 2 credits up front, 7 more for make_video, private-by-default with an opt-in public cast, and asynchronous staging where the clip starts when the look finishes. The polling instruction (list_images until completed) discloses the async contract that no structured field conveys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but nearly every sentence carries information (costs, privacy default, video staging, return values, polling). The opening sentence is an awkward fragment ('Optionally from a reference photo...') that front-loads a modifier rather than the action, which is the main structural flaw.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite ten parameters, nested objects and an output schema, the description covers the workflow end to end: input alternatives, credit confirmation, privacy semantics, video staging, returned identifiers and how to wait for the look to finish. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning: it explains that description and hints are alternative inputs for the same thing, that a reference photo does not replace the written identity, and gives content guidance (nationality, age 18+, hair, eyes, style, realism anchor).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (create a new AI influencer) plus the artifact it produces (first look), which cleanly separates it from list_characters, update_character and suggest_influencers. An agent can identify the tool without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives real selection guidance: use a reference photo via photo_file, photo_upload or photo_url, confirm credits with get_credits, and get ready-made descriptions from suggest_influencers. It never states when to prefer update_character or when not to create a new character, so it falls short of full when/when-not coverage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All ClipUGC tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.