mcpField
M
MCP Image Placeholder Server

MCP Image Placeholder Server

Local
github.com/husniadilMedia & Design12Updated 89w ago

About MCP Image Placeholder Server

MCP Image Placeholder Server is an MCP server for developers and content creators who need temporary image URLs. It supports the placehold and lorem-picsum providers and validates input parameters.

Key features

  1. 01Supports placehold and lorem-picsum
  2. 02Generates placeholder image URLs
  3. 03Validates image dimensions

Use cases

  1. 01Populate page prototypes with images
  2. 02Create temporary images for gallery examples
  3. 03Generate placeholders at specified dimensions

MCP support

The server exposes an image_placeholder tool to MCP clients, returning an image URL based on the selected provider and dimensions.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Image Placeholder Server

This is a Model Context Protocol (MCP) server that provides a tool for generating placeholder images from different providers.

Features

  • Generates placeholder images from supported providers
  • Supports two image providers:
  • Validates input parameters
  • Returns image URLs for immediate use

Requirements

  • Python 3.9+
  • uv package manager

Installation

  1. Clone this repository
  2. Set up the configuration for MCP server

Usage

The server exposes one tool:

image_placeholder

Generate a placeholder image URL based on specified parameters.

Parameters:

  • provider: The image provider to use (placehold or lorem-picsum)
  • width: The width of the image (1-10000)
  • height: The height of the image (1-10000)

Returns:

  • URL string of the generated image

Example Usage:

# Generate a 300x200 placeholder image
url = image_placeholder(provider="placehold", width=300, height=200)

# Generate a 500px square lorem-picsum image
url = image_placeholder(provider="lorem-picsum", width=500)

Configuration

To connect this server to Claude for Desktop:
  1. Add the following to your claude_desktop_config.json:
    {
        "mcpServers": {
            "image-placeholder": {
                "command": "uv",
                "args": [
                    "--directory",
                    "/ABSOLUTE/PATH/TO/PROJECT",
                    "run",
                    "main.py"
                ]
            }
        }
    }
    
  2. Restart Claude for Desktop
To connect this server to Cursor:
  1. Open Cursor Settings
  2. Head to the Features section
  3. Scroll down to the MCP Servers section
  4. Click on the Add new MCP server button
  5. Enter the following information:
    • Name: image-placeholder
    • Type: command
    • Server URL: uv --directory /ABSOLUTE/PATH/TO/PROJECT run main.py
  6. Click on the Add ↵ button

Troubleshooting

If the tool is not detected, use absolute path of the uv command, e.g.

/ABSOLUTE/PATH/TO/uv --directory /ABSOLUTE/PATH/TO/PROJECT run main.py

Example Usage and Output (Cursor)

Prompt:

Create a new directory named "example" and a file named output.html.

Then create a single modern looking page using tailwindcss: https://unpkg.com/@tailwindcss/browser@4

Show a nice header, content, and footer, showing a photo gallery.

Save this into output.html

Screenshot of Cursor Agent

Output: Example Output (Cursor)

License

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.