Skip to main content
Glama
eduard256

mcp-openai-images-audio

by eduard256
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_API_KEYYesYour OpenAI API key

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
imageA

Generate, edit, or compose images via OpenAI's gpt-image family.

BEFORE the FIRST call in a conversation, read the MCP resource image-guide://full for the full prompting guide (structure, realism rules, edit/compose modes, when to set quality/fidelity). You only need to read it once per conversation.

Mode is selected by references_paths:

  • omitted/empty -> generate from text alone

  • 1 path -> edit that image

  • 2..16 paths -> generate using them as labeled references

Model routing is automatic and reported in the response:

  • background='transparent' -> gpt-image-1.5 (gpt-image-2 rejects alpha)

  • everything else -> gpt-image-2 (flagship)

Returns metadata only — the file is written to output_path. Read the file with the Read tool only if you need to verify the result.

Prompts

Interactive templates invoked by user choice

NameDescription
image_workflowWorkflow rules for the `image` tool. Read once, follow whenever the user wants an image generated, edited, or composed.

Resources

Contextual data attached and managed by the client

NameDescription
image_guideFull prompting guide for the gpt-image-2 model exposed by the `image` tool: structure, photorealism, edit/compose modes, sizing, and anti-patterns.
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.7/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no ambiguity or overlap in tool selection.

Naming Consistency5/5

With a single tool, naming consistency is inherently perfect.

Tool Count3/5

One tool for a domain that could benefit from separate tools (e.g., generate, edit, compose) is borderline. The tool uses modes via parameters, which is acceptable but minimal.

Completeness4/5

The tool covers generate, edit, and compose operations, plus background transparency. Minor gaps exist (e.g., no explicit inpainting or variations) but overall the surface is reasonable for a single-tool server.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources