
Letz AI MCP
A Model Context Protocol server that enables Claude to generate and upscale images through the Letz AI API, allowing users to create images directly within Claude conversations.
Tools
letzai_create_image
Create an image using the LetzAI public api
letzai_upscale_image
Upscale an image using the LetzAI public api
README
LetzAI MCP Setup Guide
This guide will walk you through the process of setting up and using the LetzAI MCP (Model Context Protocol) for image generation.
Prerequisites
Before you begin, ensure that you have the following:
- Node.js installed on your system. You can download it from Node.js official site.
- Claude Desktop App installed. If you don't have it, download it from Claude Desktop App.
- LetzAI API Key. You can obtain it by visiting LetzAI API.
Setup Steps
1. Download the Git Folder
Download the repository containing the LetzAI MCP project and place it in a location outside of your Downloads folder. For example:
C:\\Users\\username\\desktop
Alternatively, you can use git clone
to clone the repository:
git clone <repository-url> C:\\Users\\username\\desktop
2. Install Dependencies
Navigate to the project folder using your terminal or command prompt:
cd C:\\Users\\username\\desktop
Run the following command to install all required dependencies:
npm install
3. Compile the Project
After installing the dependencies, compile the TypeScript files into JavaScript using the following command:
npx tsc
This will generate the compiled JavaScript files in the build
folder.
4. Restart Claude App
After running npx tsc
, you must restart the Claude Desktop App for it to recognize the updated MCP configuration and compiled files.
5. Set Up MCP Configuration in Claude Desktop App
- Open the Claude Desktop App.
- Click on the Menu Icon in the top-left corner.
- From the dropdown, select File.
- Navigate to Settings.
- Under the Developer section, you will see an option for Edit Config.
- Click on Edit Config — this will open the configuration folder.
- Locate the file
claude_desktop_config.json
and edit it as needed.
Windows Configuration:
{
"mcpServers": {
"letzai": {
"command": "node",
"args": [
"C:\\ABSOLUTE\\PATH\\TO\\PARENT\\FOLDER\\letzai-mcp\\build\\index.js"
],
"env": {
"LETZAI_API_KEY": "<Your LetzAI API Key>"
}
}
}
}
Ubuntu Configuration:
{
"mcpServers": {
"letzai": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/PARENT/FOLDER/letzai-mcp/build/index.js"],
"env": {
"LETZAI_API_KEY": "<Your LetzAI API Key>"
}
}
}
}
macOS Configuration:
{
"mcpServers": {
"letzai": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/PARENT/FOLDER/letzai-mcp/build/index.js"],
"env": {
"LETZAI_API_KEY": "<Your LetzAI API Key>"
}
}
}
}
Configuration Explanation
- command: The command to run the application. We use
node
to run the JavaScript file generated by TypeScript. - args: This is the path to the compiled
index.js
file. Make sure the path is correct according to where your files are located after compilation. If you've placed the folder atC:\\Users\\username\\desktop\\letzai-mcp
, the path will be:
C:\\Users\\username\\desktop\\letzai-mcp\\build\\index.js
6. Run the MCP Server
Now that everything is set up, you can start using the LetzAI MCP in the Claude Desktop App. The server should be ready for image generation tasks once the app is running with the correct API key in the environment.
Important: After making changes to the configuration, you must restart Claude for the changes to take effect.
7. Testing the New MCP in Claude
Click on the hammer icon to view the installed MCP tools.
Once you've set up the MCP in the Claude Desktop App, you can test it by running the following prompt:
- Create image with LetzAI using prompt: "photo of @mischstrotz drinking a beer, dressed as a knight"
This will create the image based on the provided prompt, using the model @mischstrotz from LetzAI. Claude will open the image in your preferred browser.
- Upscale this image with strength 1: https://letz.ai/image/d6a67077-f156-46d7-a1a2-1dc49e83dd91
This will upscale the image using the strength parameter 1. You can pass entire URLs, or just the LetzAI Image IDs e.g. d6a67077-f156-46d7-a1a2-1dc49e83dd91
Troubleshooting
- Node.js not found: Ensure that Node.js is installed and added to your system's PATH environment variable.
- Invalid API Key: Double-check that you have correctly added your API key under the
LETZAI_API_KEY
variable in the Claude Desktop App settings. - File Path Issues: Make sure that the path to the
index.js
file is correct. If you're unsure about the path, use the absolute path to the file.
For more detailed documentation and support, visit LetzAI Docs.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.