DollhouseMCP Logo

DollhouseMCP

Official

A comprehensive Model Context Protocol (MCP) server that enables dynamic AI persona management with ...

125 views
1 installs
Updated Jan 20, 2026
Not audited
A comprehensive Model Context Protocol (MCP) server that enables dynamic AI persona management with an integrated GitHub-powered marketplace, allowing Claude and other compatible AI assistants to activate different behavioral personas.
  1. Open the FastMCP connection interface

    • Open the FastMCP connection dialog where you have the "Install Now" button.
    • You will enter the environment variable names and values into that interface before clicking "Install Now".
  2. Prepare the required environment variable names

    • At minimum, prepare these keys (values explained in following steps):
      • GITHUB_TOKEN
      • DOLLHOUSE_PORTFOLIO_DIR
      • (optional) POSTHOG_API_KEY
      • (optional telemetry flags) DOLLHOUSE_TELEMETRY_OPTIN, DOLLHOUSE_TELEMETRY_NO_REMOTE, DOLLHOUSE_TELEMETRY
  3. Create a GitHub Personal Access Token (GITHUB_TOKEN)

    1. Sign in to github.com with the account you will use for portfolio/GitHub sync.
    2. Go to Settings → Developer settings → Personal access tokens → Tokens (classic) or Fine‑grained tokens → Generate new token.
    3. Select scopes your deployment needs (common choices):
      • For repository sync: repo (or equivalent fine‑grained repo access)
      • If the server will trigger workflows: workflow
      • If you need org-level access: read:org (or appropriate fine‑grained permissions)
    4. Create the token and copy it immediately (GitHub shows it only once).
    5. Paste this token as the value for GITHUB_TOKEN in the FastMCP interface.
  4. Choose a portfolio directory path (DOLLHOUSE_PORTFOLIO_DIR)

    1. On the machine that will run the MCP server, decide a directory to hold your portfolio (e.g., /home/you/.dollhouse/portfolio or C:\Users\You.dollhouse\portfolio).
    2. Create the directory if it does not exist and ensure the MCP process can read/write it.
    3. Enter that full path as the value for DOLLHOUSE_PORTFOLIO_DIR in the FastMCP interface.
  5. (Optional) Obtain a PostHog API key (POSTHOG_API_KEY)

    • Only needed if you want to supply your own PostHog project key (the README notes a default embedded write-only key for community telemetry).
    1. Sign in to your PostHog account and open the project you want to use.
    2. Go to Project Settings → API keys (or Keys & Tokens) and copy the project write/API key.
    3. Paste that key as POSTHOG_API_KEY in the FastMCP interface.
  6. (Optional) Set telemetry flags

    • If you want to control telemetry behavior, set one or more:
      • DOLLHOUSE_TELEMETRY_OPTIN=true (enable remote PostHog telemetry)
      • DOLLHOUSE_TELEMETRY_NO_REMOTE=true (local only, no PostHog)
      • DOLLHOUSE_TELEMETRY=false (disable all telemetry)
    • Enter the chosen flag(s) and boolean value(s) in the FastMCP interface.
  7. Enter values into the FastMCP connection interface

    • For each environment variable above, add a new entry in the FastMCP form:
      • Key: (exact env name, e.g., GITHUB_TOKEN)
      • Value: (token or path)
      • Mark secret/sensitive fields (GITHUB_TOKEN, POSTHOG_API_KEY) as secret if the interface supports it.
  8. Click "Install Now"

    • After all desired envs are filled, click the Install Now button to apply the configuration and start the MCP server.
  9. Verify the server and token access

    1. Once installed/restarted, test the MCP with a simple command (for example via Claude Desktop): list_elements type="personas"
    2. If you configured GitHub sync, verify repository access by running a sync command or checking that portfolio operations succeed.
    3. If telemetry was enabled, check logs (e.g., ~/.dollhouse/telemetry.log) or PostHog project events (if you provided a custom key).
  10. If a token is lost or needs rotation

  11. Generate a new token using the same provider steps above.

  12. Update the value in the FastMCP connection interface (replace the old value).

  13. Re-run Install Now / restart the MCP server to pick up the change.

How to Install DollhouseMCP

Install DollhouseMCP MCP server with one click through FastMCP. Choose your preferred AI development tool below:

Claude Desktop

Click "Claude Desktop" in Quick Start

Cursor IDE

Click "Cursor IDE" in Quick Start

VS Code

Click "VS Code" in Quick Start

DollhouseMCP is an officially maintained MCP server, verified by the FastMCP team.

Alternatives to DollhouseMCP

Looking for similar MCP servers? Browse other servers in the same categories on FastMCP, or check out the similar servers listed above.

Quick Start

View on GitHub

More for Memory Management

View All →

More for AI and Machine Learning

View All →

Similar MCP Servers

Report Issue

Thank you! Your issue report has been submitted successfully.

Stay ahead of the MCP ecosystem

Get the top new MCP servers, trending tools, and dev tips delivered weekly. Free, no spam, unsubscribe anytime.

Join 2,847 developers. We send one email per week.