Skip to main content
Glama
Badribn0612

img-gen

by Badribn0612
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

img-gen

An MCP (Model Context Protocol) server that provides image generation and weather services for Claude Desktop and other MCP-compatible clients.

Features

🎨 Image Generation

  • Generate images using Google's Gemini 2.5 Flash Image model

  • Automatic image compression and resizing to optimize token usage

  • Base64 encoding for seamless integration with MCP clients

  • Comprehensive logging and error handling

🌤️ Weather Services

  • Get weather alerts for US states

  • Fetch detailed weather forecasts by latitude/longitude

  • Uses the National Weather Service (NWS) API

Related MCP server: Weather MCP Server

Prerequisites

  • Python 3.11 or higher

  • uv package manager

  • Google Gemini API key (for image generation)

  • Claude Desktop (optional, for MCP integration)

Installation

  1. Clone this repository:

git clone <repository-url>
cd img_gen

  1. Install dependencies using uv:

uv sync

Configuration

Google Gemini API Key

For image generation, you need to set up your Google Gemini API key. Update the API_KEY variable in image_generation.py:

API_KEY = "your-api-key-here"

Alternatively, you can modify the code to read from an environment variable for better security.

Claude Desktop Integration

To use this MCP server with Claude Desktop, add the following configuration to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Linux: ~/.config/Claude/claude_desktop_config.json

Image Generation Server Configuration:

{
  "mcpServers": {
    "image_generation": {
      "command": "/path/to/uv",
      "args": [
        "--directory",
        "/path/to/img_gen",
        "run",
        "image_generation.py"
      ]
    }
  }
}

Weather Server Configuration:

{
  "mcpServers": {
    "weather": {
      "command": "/path/to/uv",
      "args": [
        "--directory",
        "/path/to/img_gen",
        "run",
        "weather.py"
      ]
    }
  }
}

Note: Replace /path/to/uv with your actual uv installation path (e.g., /Users/username/.local/bin/uv) and /path/to/img_gen with the absolute path to this project directory.

Usage

Running the MCP Servers

Image Generation Server:

uv run image_generation.py

Weather Server:

uv run weather.py

Image Generation

The generate_image tool accepts a text prompt and returns a generated image:

  • Tool: generate_image

  • Parameters:

    • prompt (string): A text description of the image you want to generate

  • Returns: MCP Content objects containing the generated image in base64 format

Weather Services

Get Weather Alerts

  • Tool: get_alerts

  • Parameters:

    • state (string): Two-letter US state code (e.g., "CA", "NY")

  • Returns: Active weather alerts for the specified state

Get Weather Forecast

  • Tool: get_forecast

  • Parameters:

    • latitude (float): Latitude of the location (up to 4 decimal places recommended)

    • longitude (float): Longitude of the location (up to 4 decimal places recommended)

  • Returns: Detailed weather forecast for the next 5 periods

Project Structure

img_gen/
├── image_generation.py  # MCP server for image generation using Gemini API
├── weather.py           # MCP server for weather alerts and forecasts
├── main.py              # Basic entry point
├── pyproject.toml       # Project dependencies and configuration
├── uv.lock              # Locked dependency versions
└── README.md            # This file

Image Processing

The image generation server includes automatic image optimization:

  • Max Dimension: 1024 pixels (maintains aspect ratio)

  • JPEG Quality: 85

  • Target File Size: ~500 KB

  • Format: Converts all images to JPEG for consistency

Images are automatically resized and compressed to reduce token usage while maintaining reasonable quality.

Dependencies

Key dependencies include:

  • mcp[cli] - Model Context Protocol framework

  • google-genai - Google Gemini API client

  • pillow - Image processing

  • httpx - HTTP client for weather API

See pyproject.toml for the complete list of dependencies.

Logging

Both servers include comprehensive logging:

  • Logs are written to stderr

  • Log levels: INFO, DEBUG, WARNING, ERROR

  • Includes timestamps and module names

Error Handling

  • Image generation failures return error messages via MCP

  • Weather API failures gracefully handle network issues

  • Invalid inputs are validated and return appropriate error messages

License

[Add your license here]

Contributing

[Add contribution guidelines if applicable]

Available Tools

1 tool
generate_imageC

Create images based on the prompt

Args:
    prompt: A prompt to generate the image using image generation model

Returns:
    A list of MCP Content objects containing the generated image
ParametersJSON Schema
NameRequiredDescriptionDefault
promptYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. While 'Create images' implies a generative/mutation operation, the description lacks critical behavioral details: it doesn't mention authentication requirements, rate limits, cost implications, quality expectations, or what happens when generation fails. For a generative AI tool with zero annotation coverage, this is a significant gap.

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

Conciseness4/5

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

The description is efficiently structured with clear sections (Args, Returns) and uses minimal sentences. The first sentence directly states the purpose, and subsequent sections provide necessary information without redundancy. However, the 'Args' section could be more integrated with the main description rather than appearing as a separate bullet.

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

Completeness3/5

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

Given the tool has an output schema (which covers return values) and only one parameter, the description is reasonably complete for basic understanding. However, for an AI image generation tool with no annotations, it should provide more context about behavioral characteristics like generation time, supported image formats, resolution options, or usage limitations to be truly complete.

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?

The description provides basic semantic information about the single parameter ('A prompt to generate the image using image generation model'), but with 0% schema description coverage, this doesn't fully compensate. The description doesn't specify prompt format requirements, length constraints, style guidance, or what makes an effective prompt. Baseline 3 is appropriate as the description adds some value but doesn't fully address the coverage gap.

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

Purpose4/5

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

The description clearly states the tool's purpose with 'Create images based on the prompt' - a specific verb ('Create') and resource ('images') with the mechanism ('based on the prompt'). However, without sibling tools, there's no opportunity to differentiate from alternatives, so it cannot achieve a perfect score of 5.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It simply states what the tool does without any context about appropriate use cases, prerequisites, or limitations. There's no mention of when this tool would be preferred over other image generation methods.

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
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

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool 'generate_image' has a clear, singular purpose that cannot be confused with any other tool in the set.

Naming Consistency5/5

The single tool name 'generate_image' follows a clear verb_noun pattern, and since there are no other tools, consistency is inherently perfect with no deviations or mixed conventions to evaluate.

Tool Count2/5

A single tool is too few for a server named 'img-gen', which suggests a broader image generation domain. This minimal set feels thin and incomplete, as it lacks operations like editing, upscaling, or managing generated images, which are common in such domains.

Completeness2/5

The tool surface is severely incomplete for an image generation server. While 'generate_image' covers creation, there are obvious gaps such as no tools for editing images, retrieving past generations, or handling variations, which limits agent workflows and leads to dead ends.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Gemini MCP Server

    Snehasis4321
    A
    license
    Not graded
    quality
    D
    maintenance
    Integrates Google's Gemini API with MCP-compatible clients for chat, real-time web search, knowledge queries, code/text analysis, and content generation.
    59 npm
    MIT

  • Weather MCP Server

    zsozsesz
    F
    license
    B
    quality
    D
    maintenance
    Provides weather forecasts and alerts for US locations using the National Weather Service API. Enables users to retrieve active alerts by state and detailed forecasts by coordinates via MCP tools.
    2
    -

  • weather

    qurioskill
    F
    license
    C
    quality
    C
    maintenance
    Exposes US weather data as MCP tools, resources, and prompts via the National Weather Service API, enabling clients like Claude Desktop to get alerts, forecasts, and weather briefings.
    2
    1
    -