# Leonardo.ai MCP for AI Agents AI Agent Connect > Leonardo.ai lets you run high-fidelity image generations and manage custom AI models directly through your AI agent. You can trigger complex prompts, handle image-to-image transformations, and keep an eye on your token usage without leaving your workspace. It's built for anyone who needs to move from a text idea to a polished visual asset quickly, whether you're building a brand or just exploring new aesthetics. ## Overview - **Category:** ai-frontier - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_y9qRzWWnGSVBvmQMYzSP2JGQCYBThJESo5HQfoqx/ai-agent-connect - **Tags:** generative-ai, image-generation, model-management, visual-assets, prompt-engineering, content-production ## Description Stop jumping between browser tabs just to see how a new prompt looks or to check if your custom model is actually performing the way you want. This Connector puts the entire Leonardo.ai creative suite inside your chat interface. Instead of manually clicking through menus to find the right settings, you just tell your agent what you want to see. You can start a generation, ask for a variation that expands the scene, or grab a presigned URL to feed a reference image into a new project. It handles the heavy lifting of monitoring your generation history and keeping track of your active credits, so you can focus on the actual creative direction. Because Vinkius hosts this connection, you get a reliable way to pipe these high-end visual tools into your existing workflow. It’s about turning a back-and-forth conversation into a production line for images, where your agent does the tedious work of polling for results and fetching metadata while you make the big decisions. ## Tools ### upload_init_image Get a secure URL to upload a reference image for image-to-image tasks. ### generate_image Start a new image generation based on a text prompt and specific settings. ### get_generation Check if a specific image request is finished or still processing. ### list_user_generations See a list of your most recent image generations. ### get_model Pull the specific parameters and details for any individual model. ### delete_generation Remove a specific generation entry and its associated images from your history. ### create_variation Generate an unzoom extension to expand the context of an existing image. ### list_platform_models See every public model available on the Leonardo.ai platform. ### list_custom_models View the specific fine-tuned models you've trained on your account. ### get_user Fetch your current account metrics and active user data. ## Prompt Examples **Prompt:** ``` Generate a futuristic cityscape at sunset using the Phoenix model ``` **Response:** ``` Generating image... I've triggered a request using the Phoenix model. Your generation ID is 'gen-98765'. I'll monitor the status and provide the high-resolution links as soon as they're ready. ``` **Prompt:** ``` List my last 3 image generations ``` **Response:** ``` I've retrieved your recent generations: 1) 'Cyberpunk Forest' (gen-101), 2) 'Minimalist Logo' (gen-102), and 3) 'Abstract Portrait' (gen-103). Would you like me to fetch the direct URLs for any of these? ``` **Prompt:** ``` Check my current token balance and account limits ``` **Response:** ``` Retrieving metrics for user 'alex_designer'... You currently have 1,240 tokens remaining for today. Your daily limit is 2,000. You have performed 45 generations so far in this billing cycle. ``` ## Capabilities ### Trigger image generations Start new visual projects with specific prompts and model IDs. ### Manage custom models See and interact with your own fine-tuned models alongside public ones. ### Handle image-to-image tasks Get secure URLs to upload reference photos for guided generation. ### Create visual variations Expand your existing images with unzoom and context extensions. ### Audit generation history Pull recent prompts, image URLs, and hardware data from your account. ### Monitor account metrics Track your token balance and usage limits in real-time. ## Use Cases ### Expanding a concept An artist has a portrait but needs more background. They ask the agent to use create_variation to unzoom and add a city street. ### Batch brand assets A marketer needs 20 different product shots. They ask the agent to run generate_image for 20 different prompts using a specific model. ### Auditing team spend A director wants to see how many tokens the team used this week. They ask the agent to pull data from get_user. ### Reference-based design A designer wants to turn a sketch into a 3D render. They use upload_init_image to give the agent a starting point. ## Benefits - Skip the dashboard: Use generate_image to create visuals without navigating complex menus. - Faster iterations: Use create_variation to expand your images instantly while keeping the same style. - Better model control: Browse your fine-tuned assets with list_custom_models to pick the right tool for the job. - Real-time budget tracking: Check your token balance with get_user to ensure you don't run out of credits mid-project. - Streamlined history: Quickly find old prompts and URLs using list_user_generations for consistency. ## How It Works The bottom line is you get a direct pipeline to professional image generation without ever leaving your primary workspace. 1. Connect your Leonardo.ai API key to the Connector. 2. Tell your AI agent which model or style you want to use. 3. Get your high-resolution image links and metadata directly in the chat. ## Frequently Asked Questions **Can I use Leonardo.ai to make images with my AI agent?** Yes, this Connector lets you trigger high-fidelity generations directly from Claude or Cursor. You can describe the scene, and your agent handles the rest. **How do I manage my custom models?** You can ask your agent to list your custom-trained models. It will show you what's available on your account so you can pick the right one for a project. **Can I expand an image I already made?** Yes, you can use the unzoom feature. Just ask your agent to create a variation of a specific image to add more context or background. **Does this Connector help with image-to-image?** It does. You can get secure URLs to upload reference photos, allowing your agent to guide the generation based on an existing image. **Can I see how many tokens I have left?** Yes, your agent can check your account metrics. It will tell you your remaining daily balance and how many generations you've done this cycle. **How do I find my old generations?** You can ask the agent to list your recent generations. It will pull the history so you don't have to dig through the Leonardo.ai dashboard. **Can I delete old images from my history?** Yes, you can tell your agent to delete specific generation logs and their image arrays to keep your history clean. **Can I check the progress of my image generation through my agent?** Yes. Use the `get_generation_status` tool with the Generation ID provided when you started the request. Your agent will poll the Leonardo API and return the final image URLs and metadata once the process is complete. **How do I find which AI models are available for generation?** Ask your agent to `list_platform_models` or `list_custom_models`. It will return a list of available UUIDs and model names (like Phoenix or Kino XL), which are required when triggering a new image generation request. **Can my agent perform image-to-image transformations?** Absolutely. Use the `upload_init_image` tool to acquire a secure presigned URL for your source image. Once uploaded, you can command your agent to trigger a generation that uses that image as a reference for guided AI transformations.