Exposes HuggingFace computer vision models such as zero-shot object detection as tools to extend the vision capabilities of LLMs.
Setup
This project documents no single launch command; follow its repository instructions.
MCP Vision
Groundlight
Related
More- DDINO-X MCPIDEA-ResearchOfficialImage object detection, localization, keypoints and captioning for LLMs through the DINO-X API.AI Models & Services112 Repository stars
- GGENAI EVERYDAYtushar2704A repository dedicated to exploring, experimenting with, and applying Generative AI concepts and tools in practical, everyday scenarios.AI Models & Services14 Repository stars
- PPaddleOCR MCP Server飞桨 PaddlePaddleOfficialChinaLets agents run PaddleOCR to recognize text in images and PDFs, including handwriting, and parse complex documents into JSON or Markdown.AI Models & Services91.5k Repository stars
- PPollinations MCPPollinationsOfficialLets agents generate images, text and audio through the Pollinations API and list the available models.AI Models & Services5.2k Repository stars
- MMiniMax-MCPMiniMaxOfficialOfficial MiniMax MCP server for its text-to-speech, voice cloning, image and video generation APIs; the API key must match the global or mainland API host.AI Models & Services1.6k Repository stars
- 火火山引擎实时对话式 AI MCP火山引擎OfficialChinaUse Volcengine real-time conversational AI, which combines LLM, VLM, speech recognition and TTS for real-time voice conversations with models.AI Models & Services330 Repository stars