Skip to main content
Glama

replicate

Generate or edit video clips using AI video models at a per-second price, without a plan. Jobs run in the background and save to your session's generated folder.

Instructions

Make or change a video on Replicate: the same models as Higgsfield (Seedance 2.5, Kling, Veo, ...) at a price per second of video, no plan. Returns at once; the job runs in the background and the file lands in /generated/-vN.mp4, where the Assets tab shows it. model: owner/name; leave it out for the user's default (replicate_status lists the default models, the first is the default; pick another of them when it fits better). Takes maps prompt, image (the FIRST FRAME), end_image, video, duration, aspect_ratio, resolution and audio to the model's own input names; anything else goes in params by the model's names (call replicate_model first to see its inputs, defaults and allowed values). File inputs, in those fields or params, take a session file, a take number or 'sketch' (the shot's sketch); Takes uploads them. With shot= the storyboard shot shows 'Generating' and then plays the clip (aspect ratio = the storyboard format, length = the shot's length, 4-15 s). For a shot, write a real-footage prompt from the shot's do and say; never use the sketch as the first frame (the video would look drawn): pass it only to a reference-image input if the model has one. Each job costs the user money: one job per ask, never a batch nobody asked for. No token: tell the user to open Plugins › Replicate.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoShort file name. Default: shot-<id> or the prompt's first words.
shotNoA storyboard shot id: the clip becomes that shot's video.
audioNoMake sound with the video, when the model can.
imageNoFirst frame: a session file or take still. Not a sketch.
modelNoowner/name (or owner/name:version). Leave out for the default.
videoNoA session video to change (take number or path), for models that take one.
paramsNoMore inputs by the model's own names (replicate_model lists them).
promptNoWhat the clip shows and how the camera moves.
sessionYesSession as 'Project/folder', an absolute path, or its id (from get_session). An old path still works after a rename or move.
durationNoSeconds.
end_imageNoLast frame (session file).
resolutionNoe.g. 480p (cheap drafts), 720p, 1080p.
aspect_ratioNoe.g. 16:9, 9:16, 1:1.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing that the call returns at once while the job runs in the background, exactly where the artifact lands (<session>/generated/<name>-vN.mp4) and how it is surfaced, that each job costs the user money, and the auth prerequisite. Cost and async behavior are the traits an agent most needs and they are spelled out.

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?

Front-loaded with the action, price model, and the key async/return behavior, so the most important facts come first. The body is dense and sentence-heavy with nested parentheses, but given 13 parameters, nested params, and monetary/async side effects, almost every clause carries information.

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?

There is no output schema, yet the description covers the return semantics (returns immediately; file path and Assets visibility), the cost implication, the auth path, and the shot-integration side effect. For a high-complexity open-world generation tool this is complete enough to invoke correctly.

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 routing guidance: the named fields map to the model's own input names, and everything else must go into params under the model's names. It also clarifies that image is the FIRST FRAME and sketches must not be used there. It stops short of per-parameter formats (it defers those to replicate_model).

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 and resource ('Make or change a video on Replicate') and immediately distinguishes itself from the sibling higgsfield by naming the same model family and the pricing difference. An agent can tell which video-generation tool to pick without opening either schema.

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

Usage Guidelines5/5

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

Explicit routing rules: leave model out for the user's default, consult replicate_status for defaults, call replicate_model first to see inputs/defaults/allowed values, use shot=<id> for storyboard integration, and never use the sketch as the first frame for a shot. It also states the hard constraints (one job per ask, no batches, no token → open Plugins › Replicate).

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