
An MCP server that adds image recognition to text-only models such as DeepSeek by sending images to configurable vision providers and returning textual descriptions. Supports Claude Code, Codex, Cursor, clipboard images, batch processing, and session image retrieval.
Prices and medians update for the tier you select. Caution: thin market — treat statistics as indicative.
Agents cost 0.3× MCP servers at the Pro tier.
Ranked by how closely each one matches Deepseek Eyes 2's job. Prices show each provider's Pro state; entry prices are labelled as such. Unpriced products still belong to the market.
Thin market — few comparable priced products; treat statistics as indicative.