01
Connect Medux MCP to Codex
Add the Medux remote MCP endpoint to Codex, provide an authorized credential, and confirm that the medux_text_to_image tool is available.
Codex MCP tutorial · generate
How to generate an image from text with Codex MCP and Medux
Use Codex and Medux through MCP to generate an image from a descriptive text prompt. This guide covers input preparation, the approval gate, task monitoring, and a concrete output check.
POST/api/app/v1/generate/image/text_to_image
Generate an image from a text prompt.
Open the Create Text to Image API reference →Codex-specific workflow
Run AI Text to Image as a Codex MCP task
Use the active workspace as the source of truth. Ask Codex to identify the visual prompt and supported image settings, select medux_text_to_image, 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_text_to_image through Medux MCP to generate an image from text.
First inspect and identify the visual prompt and supported image settings.
Show me the exact tool arguments before execution.
After the task completes, return the generated image and verify that the image follows the prompt and uses the requested size and format.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. The final check is explicit: confirm that the image follows the prompt and uses the requested size and format.
What this tutorial does
Medux operation
Generate an image from a text prompt.
Agent workflow
Codex selects medux_text_to_image, presents the arguments for review, calls Medux, and reports the response.
Before you start
Authentication
- Authentication is required via Authorization header.
Preconditions
- Requires a valid Authorization header and the configured request body.
- Successful requests return a Medux task record immediately. Use the task query or sync endpoints to track completion.
Prompt Codex
Start with a clear instruction that names the Medux operation and the intended inputs.
Generate an image from a text prompt.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 |
|---|---|---|---|
prompt | string | Required | Prompt text used to generate the image. |
negative_prompt | string | Optional | Optional negative prompt. |
height | integer | Optional | Output image height. Default: 1024. |
width | integer | Optional | Output image width. Default: 1024. |
seed | integer | Optional | Random seed. Use -1 to auto-generate. Default: -1. |
num_inference_steps | integer | Optional | Number of inference steps. Default: 9. |
guidance_scale | number | Optional | Guidance scale. Default: 0.0. |
cfg_normalization | boolean | Optional | Whether to enable CFG normalization. Default: false. |
cfg_truncation | number | Optional | CFG truncation value. Default: 1.0. |
max_sequence_length | integer | Optional | Maximum text sequence length. Default: 512. |
model_id | string | Optional | Text-to-image model id. Default: text-to-image-default. |
title | string | Optional | Optional task title. |
Step-by-step workflow
02
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.
03
Ask Codex to run Create Text to Image
Use one direct instruction with the intended values. Codex should select the Medux tool and show the proposed arguments before execution.
04
Review and approve the tool call
Check that the tool is medux_text_to_image and that each file ID, task ID, option, and output setting matches your request before approving it.
05
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_text_to_image
↓
Review inputs and approve the tool call
↓
Medux runs Create Text to Image
↓
Codex reports the response and outputFrequently asked questions
Can Codex use the Medux Create Text to Image API through MCP?
Codex can call the medux_text_to_image Medux MCP tool to generate an image from a 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_text_to_image. Review its arguments before approval and consult the API reference for the current contract.