Skip to main content
Glama

DollhouseMCP

by DollhouseMCP
test-output.mdโ€ข5.03 kB
# DollhouseMCP [![npm version](https://img.shields.io/npm/v/@dollhousemcp/mcp-server.svg)](https://www.npmjs.com/package/@dollhousemcp/mcp-server) [![MCP Compatible](https://img.shields.io/badge/MCP-Compatible-green)](https://modelcontextprotocol.io) [![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL--3.0-blue.svg)](https://www.gnu.org/licenses/agpl-3.0) [![Core Build & Test](https://github.com/DollhouseMCP/mcp-server/actions/workflows/core-build-test.yml/badge.svg)](https://github.com/DollhouseMCP/mcp-server/actions/workflows/core-build-test.yml) A comprehensive Model Context Protocol (MCP) server that enables dynamic AI persona management with an integrated GitHub-powered collection. DollhouseMCP allows Claude and other compatible AI assistants to activate different behavioral personas while supporting community sharing and monetization. **๐ŸŒ Repository**: https://github.com/DollhouseMCP/mcp-server **๐Ÿช Collection**: https://github.com/DollhouseMCP/collection **๐Ÿ“ฆ NPM Package**: https://www.npmjs.com/package/@dollhousemcp/mcp-server **๐ŸŒ Website**: https://dollhousemcp.com ## ๐Ÿ“ฆ Installation ### Choose Your Installation Method <table> <tr> <th>Method</th> <th>Best For</th> <th>Pros</th> <th>Cons</th> </tr> <tr> <td><strong>Local Install</strong><br>(Recommended)</td> <td>Most users, multiple configs, customization</td> <td>โœ… Multiple setups<br>โœ… Easy backup<br>โœ… No permissions</td> <td>โŒ Longer path in config</td> </tr> <tr> <td><strong>npx</strong></td> <td>Quick testing, always latest</td> <td>โœ… No install<br>โœ… Always updated</td> <td>โŒ Slower startup<br>โŒ Needs internet</td> </tr> <tr> <td><strong>Global Install</strong></td> <td>Single shared instance</td> <td>โœ… Short command</td> <td>โŒ Only one version<br>โŒ Needs sudo/admin</td> </tr> </table> --- ### Method 1: Local Installation (Recommended) Create a dedicated folder for your MCP servers and install there: ```bash # Create MCP servers directory mkdir ~/mcp-servers cd ~/mcp-servers # Install DollhouseMCP npm install @dollhousemcp/mcp-server ``` **Configure Claude Desktop:** Add to your config file: - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` - **Linux**: `~/.config/Claude/claude_desktop_config.json` ```json { "mcpServers": { "dollhousemcp": { "command": "node", "args": ["/Users/YOUR_USERNAME/mcp-servers/node_modules/@dollhousemcp/mcp-server/dist/index.js"] } } } ``` ๐Ÿ’ก **Pro tip**: Replace `/Users/YOUR_USERNAME` with your actual home directory path. --- ### Method 2: Always Latest with npx No installation needed! Configure Claude Desktop to always use the latest version: ```json { "mcpServers": { "dollhousemcp": { "command": "npx", "args": ["@dollhousemcp/mcp-server@latest"] } } } ``` ๐Ÿ“ **Note**: The `@latest` tag ensures you always get the newest version. Remove it to use npm's cached version. --- ### Method 3: Global Installation ```bash # Install globally (may require sudo/admin) npm install -g @dollhousemcp/mcp-server ``` **Configure Claude Desktop:** ```json { "mcpServers": { "dollhousemcp": { "command": "dollhousemcp" } } } ``` โš ๏ธ **Warning**: Only one version system-wide. Consider local installation for more flexibility. --- ### ๐ŸŽฏ Advanced: Multiple Configurations Want separate portfolios for different contexts? Create multiple local installations: ```bash # Personal assistant mkdir ~/mcp-servers/personal cd ~/mcp-servers/personal npm install @dollhousemcp/mcp-server # Work assistant mkdir ~/mcp-servers/work cd ~/mcp-servers/work npm install @dollhousemcp/mcp-server # Creative writing mkdir ~/mcp-servers/creative cd ~/mcp-servers/creative npm install @dollhousemcp/mcp-server ``` **Configure each with its own portfolio:** ```json { "mcpServers": { "dollhouse-personal": { "command": "node", "args": ["/Users/YOU/mcp-servers/personal/node_modules/@dollhousemcp/mcp-server/dist/index.js"], "env": { "DOLLHOUSE_PORTFOLIO_DIR": "/Users/YOU/portfolios/personal" } }, "dollhouse-work": { "command": "node", "args": ["/Users/YOU/mcp-servers/work/node_modules/@dollhousemcp/mcp-server/dist/index.js"], "env": { "DOLLHOUSE_PORTFOLIO_DIR": "/Users/YOU/portfolios/work" } } } } ``` Now you can enable/disable different configurations in Claude Desktop as needed! --- ### โœ… Verify Installation After configuring and restarting Claude Desktop, test with: ``` list_elements type="personas" ``` You should see your available personas. If not, check the [Troubleshooting](#-troubleshooting) section. --- ### ๐Ÿ“ Default Portfolio Location By default, your elements are stored in: - **macOS/Linux**: `~/.dollhouse/portfolio/` - **Windows**: `%USERPROFILE%\.dollhouse\portfolio\` Use the `DOLLHOUSE_PORTFOLIO_DIR` environment variable to customize this location.

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DollhouseMCP/DollhouseMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server