Skip to main content
Glama
aredamz

Axcel MCP

by aredamz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Generate a video

axcel_generate_video

Generate a video from text or images, wait for processing, and download it. Returns a jobId to poll status if rendering is still in progress.

Instructions

Generate a video on Axcel (text-to-video or image-to-video), wait for it and download it. Returns a jobId; if it is still processing, poll axcel_job_status with that jobId.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNotext: text-to-video. start_frame: animate startImage. start_end: from startImage to endImage. reference: 1..N reference images (+ optional reference video/audio). Default: inferred from the inputs.
audioNoGenerate sound (speech, effects) with the video. Default false.
modelYesExact model name from axcel_list_models, e.g. "Seedance 2.5", "Seedance 2.0", "Veo 3.1 Fast".
ratioNo"16:9", "9:16", "1:1", "3:4", "4:3", "21:9" as the model supports, or "auto" for image-to-video.
promptYesWhat happens in the video. In reference mode, refer to the reference images as @Image1, @Image2 ... in the order given.
confirmYesMust be true: confirms the user asked for this (it uses the Axcel plan or deletes data).
downloadNoDownload the result when done (default true).
durationNoSeconds; one of the model durations.
endImageNoLast frame (start_end).
fileNameNoFile name stem; the job id is appended.
languageNoLanguage/accent of generated speech: en (English), ms (Malay), id (Indonesian). Default en.
resolutionNo480, 720 or 1080, as the model supports.
startImageNoFirst frame (start_frame / start_end): local image path, http(s) URL or assetId.
extraInputsNoAdvanced: extra input slots for models that list them in axcel_list_models, e.g. {"style-ref": ["/path/style.png"]}.
waitSecondsNoSeconds to wait for the result before returning (default 40). If it is not done by then, poll axcel_job_status with the jobId.
startFromJobNoSeamless continuation: use the LAST frame of this earlier video job as the start frame (needs ffmpeg).
outputDirectoryNoFolder for the result (default /root/Downloads/axcel). Use the user's project folder when working in one.
referenceAudiosNoReference mode, plans with reference media: up to 3 MP3/WAV files, 2-15 s each, 15 s in total.
referenceImagesNoReference mode: 1 to the plan maximum (see axcel_status) image paths/URLs/assetIds.
referenceVideosNoReference mode, plans with reference media: up to 3 MP4/MOV files, 2-15 s each, 15 s in total.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already flag non-read-only, non-idempotent, open-world behavior, so the bar is lower. The description adds real workflow context beyond them: the call is long-running and waits, it downloads by default, it returns a jobId, and there is a documented fallback path if processing is unfinished. It does not restate the plan/credit-consumption behavior, which lives only in the schema.

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

Conciseness5/5

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

Two compact sentences, front-loaded with the action and mode scope, followed by the return value and the polling fallback. No filler or redundant restatement of the title.

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

Completeness4/5

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

For a 20-parameter, mutating, cost-incurring tool with no output schema, the description covers the essentials an agent must know: it is asynchronous, it waits, it downloads, it returns a jobId, and how to continue. Gaps remain around cost/confirmation semantics and differentiation from image-generation or sequence workflows, but the rich schema absorbs most of that burden.

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

Parameters3/5

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

Schema description coverage is 100%, so every one of the 20 parameters is already documented in the schema, and the description adds no format, default, or constraint detail beyond it. Baseline 3 is appropriate when the schema carries the full parameter burden; the only addition (jobId return) is about output, not parameters.

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 plus resource ('Generate a video on Axcel') and immediately enumerates the two supported modes (text-to-video, image-to-video). It also distinguishes itself from sibling job tools by clarifying that it waits and downloads, and that polling is the fallback. An agent can identify this 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 Guidelines3/5

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

It names one alternative with a clear triggering condition ('if it is still processing, poll axcel_job_status with that jobId'), which is genuine routing guidance. However, with siblings like axcel_generate_image, axcel_sequence_start, and axcel_download_job present, it offers no guidance on when to prefer this tool over those, and no exclusions.

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

Deploy Server

Other Tools