MCP servers for multimodal

A Codex plugin and local MCP runtime for context-bounded image generation and inspection.

MCP server that gives text-only LLM coding agents vision — analyze images via any multimodal model (mimo, Claude, Gemini, OpenAI-compatible). Works with Claude Code, Codex, Kimi, opencode, PI.

Vision-primitives MCP server for text-only LLMs: describe, locate (coordinates), OCR with bbox, annotate, crop, zoom, automated anomaly scanning, computer use — powered by Xiaomi MiMo V2.5. Single-fil

Local-first Codex plugin that indexes long videos with OCR/ASR and answers with timestamped, SHA-verified visual evidence.

A token-efficient, provider-agnostic vision layer for reasoning models via MCP.