DollhouseMCP

v2.0.32โ€ขDeveloper Toolsโ€ขstable

๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - One-line installable MCP server that adds reusable customization elements โ€” personas, skills, t

agentsaiai-toolsclaudecodex
Share:
33
Stars
0
Downloads
0
Weekly
0/5

What is DollhouseMCP?

DollhouseMCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - one-line installable mcp server that adds reusable customization elements โ€” personas, skills, t

๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - One-line installable MCP server that adds reusable customization elements โ€” personas, skills, t

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP protocol support

Use Cases

Create reusable personas
Define custom skills
Build AI agent templates
DollhouseMCP

Maintainer

LicenseAGPL-3.0
Languagetypescript
Versionv2.0.32
UpdatedApr 23, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @dollhousemcp/mcp-server

Manual Installation

npx -y @dollhousemcp/mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use DollhouseMCP

DollhouseMCP is a one-line installable MCP server that adds reusable customization elements โ€” personas, skills, templates, agents, prompts, and ensembles โ€” to any MCP-compatible AI client including Claude Desktop, Claude Code, Cursor, VS Code, Codex, Gemini CLI, Windsurf, Cline, and LM Studio. It ships with 37 starter elements and a dedicated dollhouse-expert-suite ensemble, letting developers define named behavior patterns they can activate and reuse across sessions without re-prompting. Operations use a semantic MCP-AQL query language through five endpoints (Create, Read, Update, Delete, Execute) with auto-approval for read-only actions.

Prerequisites

  • Node.js 18 or later (for npx execution)
  • An MCP-compatible client such as Claude Desktop, Claude Code, Cursor, or VS Code
  • Optional: a GitHub personal access token (GITHUB_TOKEN) for publishing custom elements to a GitHub-backed portfolio
  • Optional: write access to ~/.dollhouse/portfolio/ for persistent custom element storage
1

Run the interactive setup wizard

The easiest installation path is the browser-based wizard, which detects your installed MCP clients and adds the server configuration automatically with one click.

npx @dollhousemcp/mcp-server@latest --web
2

Or add directly to Claude Code

For Claude Code users, the single-line CLI command registers DollhouseMCP as a user-scoped MCP server without opening a browser.

claude mcp add -s user dollhousemcp -- npx -y @dollhousemcp/mcp-server
3

Configure Claude Desktop manually

For Claude Desktop, add the server entry to claude_desktop_config.json. No API keys are required for basic operation.

{
  "mcpServers": {
    "dollhousemcp": {
      "command": "npx",
      "args": ["-y", "@dollhousemcp/mcp-server"],
      "env": {
        "DOLLHOUSE_PORTFOLIO_DIR": "~/.dollhouse/portfolio/"
      }
    }
  }
}
4

Explore available elements

After connecting your client, ask DollhouseMCP to list all available elements. The 37 starter elements include personas, skills, and ensembles you can activate immediately.

5

Activate a persona or ensemble

Use natural language to activate a persona or the expert suite ensemble. DollhouseMCP's Read operations are auto-approved, so listing and activating elements requires no confirmation prompts.

DollhouseMCP Examples

Client configuration (claude_desktop_config.json)

Full configuration block for Claude Desktop with optional GitHub token for portfolio sync and custom portfolio directory.

{
  "mcpServers": {
    "dollhousemcp": {
      "command": "npx",
      "args": ["-y", "@dollhousemcp/mcp-server"],
      "env": {
        "DOLLHOUSE_PORTFOLIO_DIR": "/Users/you/.dollhouse/portfolio/",
        "GITHUB_TOKEN": "ghp_yourtoken",
        "MCP_INTERFACE_MODE": "mcpaql"
      }
    }
  }
}

Prompts to try

Example prompts for exploring and using DollhouseMCP personas, skills, and ensembles.

- "What DollhouseMCP elements do you have available?"
- "Activate the code review persona"
- "List all available Dollhouse skills"
- "Activate the dollhouse-expert-suite ensemble to help me set up DollhouseMCP"
- "Create a new persona named 'TechWriter' that responds in concise, documentation-friendly language"
- "Show me all active elements in my current Dollhouse session"

Troubleshooting DollhouseMCP

npx -y @dollhousemcp/mcp-server fails with version resolution errors

Clear the npx cache with `npm cache clean --force` and retry. If behind a corporate proxy, set the npm proxy: `npm config set proxy http://proxy.example.com:8080`. You can also pin a specific version by replacing @dollhousemcp/mcp-server with @dollhousemcp/mcp-server@<version>.

Portfolio changes are not persisted between sessions

Ensure DOLLHOUSE_PORTFOLIO_DIR points to a writable directory and that the path uses an absolute value rather than a tilde (~). On macOS/Linux the default is ~/.dollhouse/portfolio/; on Windows use %USERPROFILE%\.dollhouse\portfolio\. Create the directory manually if it does not exist: `mkdir -p ~/.dollhouse/portfolio`.

Update and Delete operations keep prompting for confirmation

This is expected behavior โ€” DollhouseMCP auto-approves only Read operations (list, search, activate). Write operations (Update, Delete, Execute) require explicit user confirmation to prevent accidental data loss. Add frequently used operations to your MCP client's allowed tools list if you want to reduce prompts.

Frequently Asked Questions about DollhouseMCP

What is DollhouseMCP?

DollhouseMCP is a Model Context Protocol (MCP) server that ๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - one-line installable mcp server that adds reusable customization elements โ€” personas, skills, t It connects AI assistants to external tools and data sources through a standardized interface.

How do I install DollhouseMCP?

Install via npm with the command: npx -y @dollhousemcp/mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with DollhouseMCP?

DollhouseMCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is DollhouseMCP free to use?

Yes, DollhouseMCP is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "dollhousemcp": { "command": "npx", "args": ["-y", "@dollhousemcp/mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide โ†’

Ready to use DollhouseMCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides