Multimodal Input Processing MCP Repositories

Generates images, text, and audio from prompts using the Pollinations APIs. It supports returning images as base64-encoded data and allows listing available models for image and text generation.

Combines text chat and image analysis capabilities to conduct multimodal conversations and handle custom queries seamlessly. Optimizes workflows with intelligent model selection and performance improvements.

The TouchDesigner MCP Server allows AI agents to interact with TouchDesigner projects by creating, modifying, and deleting project elements, as well as executing Python scripts to automate tasks.

Enables video editing through natural language commands for basic editing operations. Integrates with projects to automate video processing tasks using ffmpeg.