Access

AI video answer

How do I send video prompt instructions through MCP?

Short answer

Pass the finished prompt as a tool argument, not as hidden chat context. Include the input mode, model, duration, output, references, audio plan, final frame, and any model-specific prompt fields in the same structured request.

01

Build the prompt before the paid call

The agent can call a read-only prompt-instructions tool with the model, input mode, subject, action, camera, light, sound, and references. The tool returns a normalized prompt and warnings for incompatible controls.

The user or agent can revise that prompt before any video job starts.

02

Separate prose from settings

Prompt text directs the subject, motion, camera, scene, style, dialogue, and sound. Duration, resolution, aspect ratio, audio switch, model ID, seed, references, and maximum cost belong in typed tool fields.

This makes errors visible and stops a model from treating an API setting as part of the scene description.

03

Create with explicit approval data

The final create request includes the approved prompt, normalized settings, reference IDs, estimate or budget ceiling, and idempotency key. The server returns exactly what it accepted.

If a required reference is missing or the estimate exceeds the ceiling, the tool returns a structured error before the provider request begins.

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