Skip to main content
Glama
aurynsinclair

organon-create-image

by aurynsinclair
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

organon-create-image

MCP server for image generation using Gemini.

Features

  • Text-to-image generation via Gemini (default: gemini-3-pro-image-preview)

  • Multiple aspect ratio support (1:1, 16:9, 9:16, etc.)

  • Returns generated images both as files and inline via MCP image content type

  • Supports both AI Studio (API key) and Vertex AI (service account) backends

Related MCP server: nano-banana-mcp

Prerequisites

  • Node.js 18+

  • One of the following:

    • AI Studio: A Gemini API key from Google AI Studio

    • Vertex AI: A Google Cloud project with Vertex AI API enabled + Application Default Credentials

Setup

npm install
npm run build

Configuration

Environment Variables

Variable

Required

Default

Description

GEMINI_API_KEY

Option 1

—

AI Studio API key (takes priority over Vertex AI)

VERTEX_PROJECT

Option 2

—

Google Cloud project ID (Vertex AI)

VERTEX_LOCATION

No

us-central1

Vertex AI location

Note: Set either GEMINI_API_KEY or VERTEX_PROJECT. If both are set, GEMINI_API_KEY takes priority.

Claude Code MCP Registration

AI Studio (recommended for access to preview models):

{
  "mcpServers": {
    "create-image": {
      "command": "node",
      "args": ["/path/to/organon-create-image/dist/index.js"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Vertex AI:

{
  "mcpServers": {
    "create-image": {
      "command": "node",
      "args": ["/path/to/organon-create-image/dist/index.js"],
      "env": {
        "VERTEX_PROJECT": "your-gcp-project-id"
      }
    }
  }
}

Tools

generate_image

Generate an image from a text prompt.

Parameters:

Parameter

Type

Required

Default

Description

prompt

string

Yes

—

Text prompt for image generation (English recommended)

aspect_ratio

enum

No

"1:1"

Aspect ratio: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9

output_path

string

Yes

—

File path to save the generated image (.png)

model

string

No

"gemini-3-pro-image-preview"

Gemini model name (e.g. gemini-2.5-flash-image)

Returns: Generated image saved to output_path, plus inline image via MCP image content type.

Quality Checks

Run all quality checks at once:

npm run check:all

This executes the following checks in sequence:

Script

Check

Tool

typecheck

Type checking (strict)

tsc --noEmit

lint

Linter + cyclomatic complexity

ESLint + typescript-eslint

format:check

Code formatting

Prettier

test:coverage

Tests + coverage report

Vitest + V8

audit

Known CVE scan

npm audit

audit:lockfile

Lockfile integrity

lockfile-lint

sast

Security static analysis

Semgrep

Note: Semgrep requires a separate installation via pip. See QUALITY.md for setup details.

License

MIT

Available Tools

1 tool
generate_imageGenerate ImageA

Generate an image from a text prompt using Gemini. The image is saved to the specified file path and also returned inline. Supports various aspect ratios.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoGemini model name for image generation. Default: gemini-3-pro-image-preview. Example: gemini-2.5-flash-image
promptYesText prompt for image generation. English recommended. More specific and detailed prompts yield better results.
output_pathYesFile path to save the generated image (.png). Example: C:/Users/palan/Pictures/output.png
aspect_ratioNoAspect ratio of the output image. Default: 1:1.1:1

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description itself discloses key behaviors: 'The image is saved to the specified file path and also returned inline.' This reveals the side-effect of file creation and the dual output. However, it does not mention overwrite behavior, API requirements, or failure modes, which would add more transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, immediately states the core action, and wastes no words. It is front-loaded and easy for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a relatively simple tool with a well-described schema, the description covers the main aspects: generation, output location, inline return, and aspect ratios. It lacks details about the inline return format or any prerequisites, but it is sufficiently complete for common use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters clearly. The description adds no extra parameter information beyond summarizing 'text prompt' and 'file path.' Thus, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Generate an image from a text prompt using Gemini.' It specifies the action (generate), the resource (image), and the method (text prompt + Gemini). It also mentions the output behavior (saved to file, returned inline), making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by explaining what the tool does, but it lacks explicit guidance on when to use it or prerequisites. It mentions 'Supports various aspect ratios' as a feature but doesn't give specific use-case directives. With no siblings, this is acceptable but not exemplary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.1.0
    • First observedgenerate_image
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.3/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusion or overlap. The tool's purpose is clearly defined and unambiguous.

Naming Consistency5/5

The tool name 'generate_image' follows a consistent verb_noun pattern, and with only one tool, there are no inconsistencies to evaluate.

Tool Count5/5

A single tool is well-scoped for a server dedicated exclusively to image generation. The narrow domain requires no additional tools.

Completeness5/5

The tool fully covers the core operation of generating an image from a prompt, including file saving and aspect ratio support. No obvious gaps exist for the stated purpose.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers