Access

AI video answer

What tools should an AI video MCP server expose?

Short answer

Use separate tools for listing models, reading one model, estimating cost, building prompt instructions, creating a job, checking status, cancelling a job, and retrieving the final result.

01

Start with read-only discovery

List models and get model details should expose prices, supported inputs, duration, resolution, aspect ratio, audio, reference limits, and prompt rules. Estimate cost should remain read-only.

A prompt-instructions tool can return the best structure for the chosen model and input mode without starting a paid job.

02

Use one paid create action

Create video receives the final prompt, model, settings, references, cost ceiling, and idempotency key. Its description should clearly state that it starts a billable generation job.

The immediate result returns a job handle and accepted settings. Long-running work continues outside the original tool call.

03

Manage the job lifecycle

Get status returns queued, running, completed, failed, or cancelled states with progress and error details. Cancel stops a job when the provider still allows it.

Get result returns final metadata and a resource link or URL for the video, poster frame, logs, and any machine-readable generation data.

Related guide

Get the full context.

AI video MCP server for Claude and agent workflows

Connect AI agents to video generation with MCP tools for model discovery, price estimates, prompt building, job creation, spending limits, status, and results.

Read the mcp ai video API guide

Current prices

Compare each video route.

Open full pricing →
ModelCompared rateCre8vid price5 sec10 secSavings
MiniMax H3MiniMax$0.065$0.029$0.145$0.2955% less
Wan 3.0Alibaba$0.050$0.025$0.125$0.2550% less
Kling 3.0Kuaishou$0.084$0.039$0.195$0.3954% less
Seedance 2.5ByteDance$0.144$0.069$0.35$0.6952% less
Veo 3.1 Fast + audioGoogle$0.100$0.049$0.24$0.4951% less