DollhouseMCP MCP server

Read from the package source without running it. The installed server may list more.

• MyAgent

  Task executor

• MyPersona

  A helpful assistant

• activate_element

  Activate a specific element by name

• browse_collection

  Browse content from the DollhouseMCP collection by section and content type. Content types include personas (AI behavioral profiles), skills, agents, and templates. When users ask for 'personas', they're referring to content in the personas type.

• check_github_auth

  Check current GitHub authentication status. Shows whether you're connected to GitHub, your username, and what actions are available. Use when users ask 'am I connected to GitHub?', 'what's my GitHub status?', or similar questions.

• clear_github_authwrite action

  Remove GitHub authentication and disconnect from GitHub. Use when users say 'disconnect from GitHub', 'remove my GitHub connection', 'clear authentication', or want to switch accounts.

• clear_user_identity

  Clear user identity and return to anonymous mode

• complete_agent_goal

  Signal that the agent has completed its goal. This marks the goal as complete, updates decision outcomes, and calculates performance metrics. Use this when all success criteria have been met.

• configure_collection_submission

  Configure automatic collection submission settings. When enabled, the submit_collection_content tool will automatically create a submission issue in the DollhouseMCP collection repository after uploading to your portfolio.

• configure_indicator

  Configure how active persona indicators are displayed

• configure_oauth

  Configure GitHub OAuth client ID for authentication. If no client_id provided, shows current configuration status. If client_id provided, validates format and saves it to config. Use when users need to set up OAuth or check their configuration.

• continue_agent_execution

  Continue executing an agent from its current state. Use this to resume after interruption or start the next step in a multi-step workflow. Returns the agent's context including previous state, allowing the LLM to pick up where it left off.

• create_elementwrite action

  Create a new element of any type

• deactivate_element

  Deactivate a specific element

• delete_elementwrite action

  Delete an element and optionally its associated data files

• dollhouse_config

  Manage DollhouseMCP configuration settings. Replaces set_user_identity, get_user_identity, and clear_user_identity tools.

• edit_element

  Edit an existing element using nested input objects (deep-merged with existing)

• execute_agentwrite action

  Execute an agent with a goal. Activates configured elements and returns context for LLM-driven agentic loop. The agent configuration defines a goal template that is filled with provided parameters.

• find_similar_elements

  Find elements that are semantically similar to a given element using NLP scoring (Jaccard similarity and Shannon entropy). Returns elements with similarity scores and relationships.

• get_active_elements

  Get information about currently active elements of a specific type

• get_agent_state

  Query the current state of an agent, including active goals, decision history, progress, and execution context. Use this to understand what the agent has done and what remains to be completed.

• get_build_info

  Get comprehensive build and runtime information about the server

• get_collection_cache_health

  Get health status and statistics for the collection cache system. This helps monitor cache performance and identify any issues with offline browsing capability.

• get_collection_content

  Get detailed information about content from the collection. Use this when users ask to 'see details about a persona' or 'show me the creative writer persona'. Personas are a type of content that defines AI behavioral profiles.

• get_collection_submission_config

  Get current collection submission configuration settings

• get_element_details

  Get detailed information about a specific element

• get_element_relationships

  Get all relationships for a specific element, including semantic similarities, verb-based connections, and cross-element references.

• get_indicator_config

  Get current persona indicator configuration

• get_relationship_stats

  Get statistics about the Enhanced Index relationships, including total counts by type, most connected elements, and index health metrics.

• get_user_identity

  Get current user identity information

• import_persona

  Import a persona from a file path or JSON string

• init_portfolio

  Initialize a new GitHub portfolio repository for storing your DollhouseMCP elements. Creates the repository structure with proper directories and README.

• install_collection_content

  Install AI customization elements FROM the DollhouseMCP collection TO your local portfolio. Use this when users ask to download/install any element type (personas, skills, templates, agents, or memories) from the collection. Examples: 'install the creative writer persona from the collection', 'get the code review skill from collection', 'download the meeting notes template from collection', 'get t

• list_elements

  List all available elements of a specific type with optional pagination, filtering, and sorting

• mcp_aql_deletewrite action

  Destructive operations that remove data. Supported operations: … Element types: … These operations remove data. Use with caution. ⚠️ SECURITY: Do not auto-allow this endpoint in your host settings (e.g., Claude Code settings.json). Each delete operation should require explicit human approval. Auto-allowing bypasses the per-operation confirmation gate, leaving only element deny policies as protecti

• mcp_aql_updatewrite action

  Modifying operations that overwrite data. Supported operations: … Element types: … These operations modify existing data, potentially overwriting previous values. Note: Memories are append-only and do not support edit_element. Use addEntry (CREATE) to add new entries. Quick start example: { operation: "edit_element", element_type: "persona", params: { element_name: "MyPersona", input: { descriptio

• oauth_helper_status

  Get detailed diagnostic information about the OAuth helper process. Shows if authentication is in progress, process health, timing, and any errors. Use when troubleshooting authentication issues or checking if OAuth flow is working.

• portfolio_config

  Configure portfolio settings such as auto-sync preferences, default visibility, submission settings, and repository preferences.

• portfolio_element_manager

  Manage individual elements between your local portfolio and GitHub repository. USE THIS TO DOWNLOAD/UPLOAD INDIVIDUAL PERSONAS, SKILLS, OR OTHER ELEMENTS! When a user asks to 'download X persona from my GitHub' or 'upload Y skill to GitHub', use this tool. Operations: 'download' (GitHub→local), 'upload' (local→GitHub), 'list-remote' (see what's on GitHub), 'compare' (diff local vs GitHub). FUZZY M

• portfolio_status

  Check the status of your GitHub portfolio repository including repository existence, elements count, sync status, and configuration details.

• record_agent_step

  Record a step in the agent's execution, including progress, findings, and outcome. Use this to document what the agent has done, what it learned, and whether the step succeeded. This creates an audit trail, enables resumption, and returns an autonomy directive indicating whether to continue or pause.

• reload_elements

  Reload elements of a specific type from the filesystem

• render_template

  Render a template element with provided variables

• search_all

  Search across all available sources (local portfolio, GitHub portfolio, and collection) for elements. This provides unified search with duplicate detection and version comparison across all three tiers of the DollhouseMCP ecosystem.

• search_by_verb

  Search for elements that can handle a specific action verb (e.g., 'analyze', 'create', 'debug'). Uses verb trigger patterns to find matching elements.

• search_collection

  Search for content in the collection by keywords. This searches all content types including personas (AI behavioral profiles that users activate to change AI behavior), skills, agents, prompts, etc. When a user asks to 'find a persona', search in the collection.

• search_collection_enhanced

  Enhanced search for collection content with pagination, filtering, and sorting. Use this for advanced searches when users need specific content types or want to browse results in pages.

• search_portfolio

  Search your local portfolio by content name, metadata, keywords, tags, or description. This searches your local elements using the portfolio index for fast metadata-based lookups.

• session-notes

  Session context and notes

• set_user_identity

  Set your username for persona attribution and collection participation

• setup_github_auth

  Set up GitHub authentication to access all DollhouseMCP features. This uses GitHub's secure device flow - no passwords needed! Use this when users say things like 'connect to GitHub', 'set up GitHub', 'I have a GitHub account now', or when they try to submit content without authentication.

• submit_collection_contentwrite action

  Submit a single element TO the DollhouseMCP community collection (via your GitHub portfolio). This first uploads the element to your personal GitHub portfolio, then creates a submission issue for the community collection. Use this when users want to share their custom elements with the community. This handles all content types including personas (AI behavioral profiles).

• sync_portfolio

  Sync ALL elements in your local portfolio with your GitHub repository. By default uses 'additive' mode which only adds new items and never deletes (safest). Use 'mirror' mode for exact sync (with deletion confirmations). Use 'backup' mode to treat GitHub as backup source. ALWAYS run with dry_run:true first to preview changes. For individual elements, use 'portfolio_element_manager' instead.

• validate_element

  Validate an element for correctness and best practices

• Code scan813 source files scanned20/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 15 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

DollhouseMCP: common questions

Is DollhouseMCP MCP server safe?

Yes, by our scan: it is graded A (86/100). Read the DollhouseMCP safety report

How do I install DollhouseMCP?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does DollhouseMCP need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is DollhouseMCP maintained?

The last commit was 16 days ago (2026-09-05). The latest release is v2.0.42.