Scrivener Bridge MCP

A standalone Model Context Protocol (MCP) server that provides direct, read-only access to a live Scrivener project (.scriv), combined with an indirect writing workflow via an Inbox folder.

Features

• Parse Scrivener's internal .scrivx XML file to extract the Binder hierarchy.
• Convert internal .rtf files into clean, readable text for AI context.
• Write drafted scenes or notes to a designated Staging Inbox for safe drag-and-drop importing.

Setup

1. Clone or download this repository.
2. Install dependencies: pip install -r requirements.txt
3. Add the server to your AI platform's MCP configuration.

Tools Provided

• get_binder_tree(scriv_path): Returns the structure of the Scrivener project.
• read_scene(scriv_path, scene_uuid): Reads and converts the text of a specific scene.
• write_to_inbox(inbox_path, filename, content): Saves a markdown file to the author's staging folder.