MCP tools

Your AI agent selects and calls these tools automatically based on your prompts — you don’t invoke them by hand. Each tool has its own page with full parameter details. See the MCP server overview for what the server does and Setup for connecting your client.

These are the creative server tools (generation, models, workflows, files). Workspace administration lives on a separate server — see Management MCP.

Instructions

These tools return platform guidance. Your AI agent calls them automatically to understand how to use Layer — you don’t need to invoke them directly.

• get_instructionsGet general instructions for using the Layer MCP server.
• get_workflow_instructionsGet detailed instructions for running generation workflows.
• get_forge_instructionsGet detailed instructions for running forge (direct model execution).

Workspaces

List and inspect the Layer workspaces you belong to.

• list_workspacesList every workspace the current user belongs to.
• get_workspaceGet details for a single workspace including Creative Units balance.

Models

Discover and inspect the generative models available to your workspace.

• get_model_recommendationsGet curated model recommendations for common game asset creation tasks.
• list_modelsList available AI models/styles in a workspace.
• get_modelGet full details for a specific model/style.

Workflows

Workflows are multi-step pipelines built in the Layer app’s Blueprint editor.

• list_workflowsList available generation workflows (published blueprints) in a workspace.
• estimate_workflow_priceEstimate the Creative Units price of running a workflow before executing it.
• execute_workflowExecute a workflow run to produce images or videos via a multi-step pipeline.
• get_workflow_runCheck status of a running workflow.
• cancel_workflow_runCancel a running workflow.

Forge

Forge runs a single model directly, giving you full control over parameters.

• estimate_forge_priceEstimate the Creative Units price of a forge run before executing it.
• execute_forgeExecute a forge run to generate images, videos, 3D models, or audio.
• get_forge_runCheck status of an inference run launched with execute_forge.

Video timeline

Compose assets the user already has into a single finished video, estimate the cost first, and poll the render.

• estimate_video_timeline_priceEstimate the Creative Units price of a video timeline render without rendering anything.
• render_video_timelineCompose assets the user already has into ONE finished video and return immediately with a handle.
• get_generation_runCheck status of a generation run launched with a generation tool (e.g.

Files

Upload local files or public URLs for use as inputs in workflows and forge.

• request_file_upload_urlRequest a signed URL to upload a file directly to storage.
• upload_fileUpload an image or video file from a URL for use as workflow input.