Picsha AI is a Model Context Protocol (MCP) server: AI-native digital asset management: semantic search, generative image edits, and CDN delivery. As an MCP server it plugs straight into AI assistants, exposing its functionality as tools the model can invoke on your behalf.
You can run Picsha AI two ways: connect to the hosted endpoint at https://api.picsha.ai/v1/mcp with no local install, or run it on your own machine via the npm package @picsha-ai/mcp-server. Configuration happens through environment variables — you'll need PICSHA_API_KEY. The current release is v1.0.1.
You'll find Picsha AI in the Search category here on mcp.site; it connects to Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and any other MCP client — see the install snippets below. If you maintain Picsha AI for picsha.ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
