How do I run AI Image to Video with Codex MCP?

Codex can use medux_video_generate_image_to_video through Medux MCP to animate a source image into a video using a text prompt. The workflow identifies the exact inputs, reviews the tool arguments, monitors processing, and verifies the returned result.

Codex MCP tutorial · generate

How to turn an image into a video with Codex MCP and Medux

Q: Which MCP tool does this tutorial use?

This workflow uses medux_video_generate_image_to_video . Review its arguments before approval and consult the API reference for the current contract.

Use Codex and Medux through MCP to animate a source image into a video using a text prompt. This guide covers input preparation, the approval gate, task monitoring, and a concrete output check.

POST/api/app/v1/generate/video/image_to_video

Generate a video from a source image and text prompt.

Open the Create Image to Video API reference →

Codex-specific workflow

Run AI Image to Video as a Codex MCP task

Use the active workspace as the source of truth. Ask Codex to identify the source image, motion prompt, duration, and supported generation settings, select medux_video_generate_image_to_video, and keep the Medux task ID and returned output with the rest of the project. Naming the input roles and the expected result prevents an agent from guessing which file should be used where.

Codex prompt pattern

In this workspace, use medux_video_generate_image_to_video through Medux MCP to turn an image into a video.
First inspect and identify the source image, motion prompt, duration, and supported generation settings.
Show me the exact tool arguments before execution.
After the task completes, return the generated image-to-video clip and verify that the output follows the requested motion while retaining the source subject and composition.

Approval gate

Before approving the call, compare the selected tool, file or asset IDs, ordering, timing, and output settings with the request. If a local filename was mapped to an uploaded Medux file ID, keep that mapping visible so it can be audited later.

Result verification

Let Codex monitor an asynchronous task until it reaches a terminal state, then save or report the generated image-to-video clip. The final check is explicit: confirm that the output follows the requested motion while retaining the source subject and composition.

What this tutorial does

Medux operation

Generate a video from a source image and text prompt.

Agent workflow

Codex selects medux_video_generate_image_to_video, presents the arguments for review, calls Medux, and reports the response.

Before you start

Authentication

Authentication is required via Authorization header.

Preconditions

Upload the source image and create a file reference before calling this endpoint.
Requires an uploaded image file id and a non-empty prompt.
Also accepts optional duration seconds, clarity, aspect ratio, and model id.

Prompt Codex

Start with a clear instruction that names the Medux operation and the intended inputs.

Generate a 5 second 720P 16:9 video from uploaded image {file id} and this motion prompt using model id wan-2-6-image-to-video. This model requires Starter or higher.

Request fields to review

Confirm these values before approving the MCP tool call. The linked API page remains the source of truth for current limits and response semantics.

Field	Type	Requirement	Purpose
`aspect_ratio`	string	Optional	Requested output aspect ratio, for example 16:9 or 9:16.
`clarity`	string	Optional	Requested output clarity, for example 720P or 1080P.
`duration_seconds`	int32	Optional	Requested output duration in seconds.
`file_id`	string	Optional	Provide the value described in the API reference.
`model_id`	string	Optional	Stable public Medux model identifier.
`prompt`	string	Optional	Provide the value described in the API reference.
`title`	string	Optional	Provide the value described in the API reference.

Step-by-step workflow

Connect Medux MCP to Codex

Add the Medux remote MCP endpoint to Codex, provide an authorized credential, and confirm that the medux_video_generate_image_to_video tool is available.

Prepare the required inputs

Prepare the source files, asset IDs, text, or settings required by the operation. Upload local media first when the tool requests file IDs.

Ask Codex to run Create Image to Video

Use one direct instruction with the intended values. Codex should select the Medux tool and show the proposed arguments before execution.

Review and approve the tool call

Check that the tool is medux_video_generate_image_to_video and that each file ID, task ID, option, and output setting matches your request before approving it.

Check the Medux response

If Medux returns an asynchronous task, let the agent monitor it until completion; otherwise review the immediate response and save any result identifiers or output URLs.

Workflow recap

User goal
  ↓
Codex selects medux_video_generate_image_to_video
  ↓
Review inputs and approve the tool call
  ↓
Medux runs Create Image to Video
  ↓
Codex reports the response and output

Frequently asked questions

Can Codex use the Medux Create Image to Video API through MCP?

Codex can call the medux_video_generate_image_to_video Medux MCP tool to generate a video from a source image and text prompt. This guide covers the required inputs, approval flow, result handling, and the matching API reference.

Which MCP tool does this tutorial use?

This workflow uses medux_video_generate_image_to_video. Review its arguments before approval and consult the API reference for the current contract.