deepseek-vision-mcp is an MIT-licensed MCP server that adds image understanding to DeepSeek and other text-only language models. It routes image requests through third-party OpenAI-compatible vision APIs for developers building multimodal workflows.
In the Frameworks & runtimes space, deepseek-vision-mcp takes a focused approach. It focuses on adding image understanding to text-only language models without implementing vision API integration from scratch. deepseek-vision-mcp is an open-source project aimed at AI developers building MCP-based multimodal workflows. deepseek-vision-mcp is open source under the MIT license. It ships for the command line and API, and it can be self-hosted.
Behind deepseek-vision-mcp is GOU-GEE, and it first shipped in 2026. The project is developed in the open on GitHub with 26 commits in the last 90 days. Among its 5 catalogued features are image understanding, MCP server, and Vision API routing. It exposes integrations via an MCP server and a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do