AI Workflows
Picora is built as a resource hosting platform for AI workflows. This section is about using that: what an assistant can actually do with your library, and the prompts that make it happen.
What your assistant can do
Modern AI assistants (Claude Desktop, Cursor, Moraya, …) speak the Model Context Protocol — a standard way for them to call external tools. Picora exposes 19 MCP tools covering the full resource lifecycle:
- Upload images / videos / audio / Markdown documents
- List, search and inspect your library
- Rename resources and flip visibility
- Read plan and quota counters
- Browse, read and batch-sync knowledge bases
- Delete (with mandatory dry-run protection)
Once connected, you can ask:
“Upload the README I’m editing to Picora and give me the link.” “List all images I uploaded this week, sort by size.” “Clean up videos older than 90 days. Dry-run first.”
What’s inside
- Overview — why route work through an assistant, the security model, MCP versus the raw API
- Moraya — one-click image hosting plus MCP, in one editor
- Prompt templates — battle-tested prompts for common workflows
- Tool catalog — a domain-grouped index of the 19 tools, linking into the full reference
Where setup lives
| You want to… | Go to |
|---|---|
| Connect Claude Desktop or Cursor | MCP → Quickstart |
| Know exactly what a tool accepts | MCP → Tool Reference |
| Use the hosted endpoint instead of a local install | MCP → Remote MCP |
| Understand scopes, plan gates and rate limits | MCP → Concepts |