DollhouseMCP

Enables dynamic persona management from markdown files with local creation, GitHub marketplace integration, and behavioral switching capabilities for role-playing and domain-specific customization.

DollhouseMCP enables dynamic AI persona management from markdown files, allowing Claude and other AI assistants to activate and switch between different behavioral personas stored locally or from a GitHub-based marketplace. Built by Mick Darling using TypeScript with the Model Context Protocol SDK, it offers persona activation/deactivation, local persona creation and editing with guided interfaces, marketplace browsing and installation from the DollhouseMCP-Personas repository, user identity management for attribution, and persona validation with comprehensive metadata support including categories, triggers, pricing, and content flags. The implementation features automatic unique ID generation, GitHub API integration for marketplace operations, submission workflows through GitHub issues, and robust persona loading with fallback defaults, making it valuable for AI assistants that need role-playing capabilities, content creators building character libraries, educational applications requiring different teaching styles, and developers who want to customize AI behavior for specific domains or use cases.