"Express" matching MCP servers:

Enables text-to-image generation and image editing or composition with Google's Gemini image models via MCP tools, prompts, and resources. Supports automatic model selection, aspect ratio and resolution control, curated prompt templates, and three credential modes (Gemini API key, Vertex AI Express Mode, or ADC).

Enables coding agents to inspect, patch, validate, diff, and execute RunningHub / ComfyUI workflows through structured graph tools (13 total) over MCP, routing parameter changes to nodeInfoList and topology changes to full workflow JSON, and returning structured browser-fallback requests when only the UI can express an operation.

Agentic AI instruction encoding. 86.8% smaller than JSON. Inference-free decode by table lookup. 342 opcodes, 26 namespaces, three conformant SDKs. Confirmed over LoRa mesh radio. Apache 2.0 with express patent grant.