Connect Medux MCP to Codex
Add the Medux remote MCP endpoint to Codex, provide an authorized credential, and confirm that the medux_remove_video_object tool is available.
Use Codex and Medux through MCP to remove a selected object from a video using mask regions. This guide covers input preparation, the approval gate, task monitoring, and a concrete output check.
POST/api/app/v1/process/video/remove_video_object
Remove an object from a video by mask regions.
Open the Remove Video Object API reference →Codex-specific workflow
Use the active workspace as the source of truth. Ask Codex to identify the source video and precise mask regions for the object to remove, select medux_remove_video_object, 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.
In this workspace, use medux_remove_video_object through Medux MCP to remove an object from a video.
First inspect and identify the source video and precise mask regions for the object to remove.
Show me the exact tool arguments before execution.
After the task completes, return the cleaned video and verify that the intended object is removed through the required frames without damaging unrelated regions.
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.
Let Codex monitor an asynchronous task until it reaches a terminal state, then save or report the cleaned video. The final check is explicit: confirm that the intended object is removed through the required frames without damaging unrelated regions.
Remove an object from a video by mask regions.
Codex selects medux_remove_video_object, presents the arguments for review, calls Medux, and reports the response.
Start with a clear instruction that names the Medux operation and the intended inputs.
Remove an object from a video by mask regions.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 |
|---|---|---|---|
input_file_id | string | Required | Input video file id. |
mask_regions | object | Required | Regions to remove, e.g. [[x, y, width, height]]. |
model_id | string | Optional | Model Default: remove-video-object-default. |
title | string | Optional | Optional task title. |
Add the Medux remote MCP endpoint to Codex, provide an authorized credential, and confirm that the medux_remove_video_object tool is available.
Prepare the source files, asset IDs, text, or settings required by the operation. Upload local media first when the tool requests file IDs.
Use one direct instruction with the intended values. Codex should select the Medux tool and show the proposed arguments before execution.
Check that the tool is medux_remove_video_object and that each file ID, task ID, option, and output setting matches your request before approving it.
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.
User goal
↓
Codex selects medux_remove_video_object
↓
Review inputs and approve the tool call
↓
Medux runs Remove Video Object
↓
Codex reports the response and outputCodex can call the medux_remove_video_object Medux MCP tool to remove an object from a video by mask regions. This guide covers the required inputs, approval flow, result handling, and the matching API reference.
This workflow uses medux_remove_video_object. Review its arguments before approval and consult the API reference for the current contract.
Quick answer
Codex can use medux_remove_video_object through Medux MCP to remove a selected object from a video using mask regions. The workflow identifies the exact inputs, reviews the tool arguments, monitors processing, and verifies the returned result.
Codex can use medux_remove_video_object through Medux MCP to remove a selected object from a video using mask regions. The workflow identifies the exact inputs, reviews the tool arguments, monitors processing, and verifies the returned result.
Related topics: Remove an Object from Video · Remove an Object from Video with Codex MCP · Medux MCP tutorial
Build with the API
Use the API reference to automate this workflow, or follow the matching guide in our official GitHub repository.