DollhouseMCP
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- version-control
- Source
- PulseMCP
- Repository
- github.com/dollhousemcp/mcp-server
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve DollhouseMCP from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.