ai-vision
tan-yong-sheng/ai-vision-mcp
Image, video and object-detection analysis with Google Gemini and Vertex AI for UI/UX evaluation, visual regression testing and interface understanding.
- Local integrations
Installation, supported tools and required credentials are maintained by the project.
Project details
- GitHub stars
- 80
- Language
- TypeScript
- License
- MIT
- Forks
- 16
- Latest release
- v0.0.76mo ago
- Activity
- updated 6mo ago
- Platforms listed
- macOS, Windows, Linux
First MCP server?Start with the basics
Exercises all features of the MCP protocol.
Local screen and audio capture with timestamped indexing, SQL and embedding storage, semantic search, history analysis and event-triggered actions.
Use Apify Actors, pre-built cloud tools, to extract data from websites, e-commerce, social media, search engines, maps and more.
Extract and convert YouTube video information.
Control the FluxDown multi-protocol download manager (HTTP, FTP, BitTorrent, HLS): add, list, pause, resume and remove downloads and manage queues.
Interact with Obsidian via a REST API.
Access Azure services including Storage, Cosmos DB and Azure Monitor.
Integration platform connecting AI agents to many services through one interface, with OAuth, scaling and monitoring.