AI Editing: Payload MCP
An MCP wrapper around Payload CMS that gives compatible AI assistants typed access to content editing, schema inspection, and media browsing. Built and maintained by Nodebrush.
The brief
Large content migrations are traditionally a grind. You either click through an admin panel row by row, or you write one-off scripts against the API. The Model Context Protocol gives AI assistants direct, typed access to a system's tools, so we built a proper MCP server for Payload. Editorial work that used to demand either patience or custom code now runs through ordinary conversation, with Payload's validation, access control, and lifecycle hooks still applied to every change.
What we built
An open MCP server
Our server speaks to Payload through its local API, so every change runs through the same validation, access control, and lifecycle hooks that apply to a human editor in the admin panel. The Model Context Protocol is an open standard, so the server works with any AI assistant that supports MCP rather than locking you to one specific product.
Typed tool schemas
Each tool ships with a typed schema describing exactly what every collection expects. The assistant doesn't have to guess from documentation; it understands the shape of each collection at the moment of the call, so a wrong field type or a missing required value is caught up front rather than producing broken content.
Visual media browsing
The media tool generates contact sheets of every uploaded image on demand, so the assistant picks the right picture for a page or post by looking at it rather than guessing from filenames.
Drafts by default
Every write goes through Payload's draft system. The assistant proposes, a human reviews, and a human publishes. Nothing reaches the live site without someone signing off on it.