DollhouseMCP

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 elements that are semantically similar to a given element using NLP scoring.

Get information about currently active elements of a specific type

Query the current state of an agent, including active goals, decision history, progress, and execution context.

Get comprehensive build and runtime information about the server

Get health status and statistics for the collection cache system.

Get detailed information about content from the collection.

Get current collection submission configuration settings

Get detailed information about a specific element

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

Get current persona indicator configuration

Get statistics about the Enhanced Index relationships.

Get current user identity information

Import a persona from a file path or JSON string

Initialize a new GitHub portfolio repository for storing your DollhouseMCP elements.

Install AI customization elements FROM the DollhouseMCP collection TO your local portfolio.

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

Description is built at runtime.

Additive, non-destructive operations. Supported operations: create_element, import_element, addEntry, activate_element, install_collection_content, submit_collection_content, init_portfolio, sync_portfolio, portfolio_element_manager, setup_github_auth, configure_oauth, import_persona Element types: persona, skill, template, agent, memory, ensemble These operations add new data without removing or overwriting existing content. Quick start examples: { operation: "create_element", element_type: "persona", params: { element_name: "MyPersona", description: "A helpful assistant", instructions: "…

Destructive operations that remove data. Supported operations: delete_element, clear, clear_github_auth Element types: persona, skill, template, agent, memory, ensemble These operations remove data. Use with caution. Quick start examples: { operation: "delete_element", element_type: "persona", params: { element_name: "MyPersona" } } { operation: "clear", params: { element_name: "MyMemory" } } Discover required parameters: { operation: "introspect", params: { query: "operations", name: "delete_element" } }

Execution lifecycle operations for executable elements (agents, workflows, pipelines). Supported operations: execute_agent, get_execution_state, record_execution_step, complete_execution, continue_execution These operations manage runtime execution state. Unlike CRUD operations (which manage definitions), Execute operations handle the execution lifecycle: - execute_agent: Start a new execution - get_execution_state: Query execution progress and findings - record_execution_step: Record step completion or progress - complete_execution: Signal successful completion - continue_execution: Resume …

Safe, read-only operations. Supported operations: search, list_elements, get_element, get_element_details, search_elements, query_elements, get_active_elements, validate_element, render, export_element, deactivate_element, introspect, browse_collection, search_collection, search_collection_enhanced, get_collection_content, get_collection_cache_health, portfolio_status, portfolio_config, search_portfolio, search_all, check_github_auth, oauth_helper_status, dollhouse_config, get_build_info, find_similar_elements, get_element_relationships, search_by_verb, get_relationship_stats Element types: …

Modifying operations that overwrite data. Supported operations: edit_element Element types: persona, skill, template, agent, memory, ensemble These operations modify existing data, potentially overwriting previous values. Quick start example: { operation: "edit_element", element_type: "persona", params: { element_name: "MyPersona", input: { description: "Updated description" } } } Discover required parameters: { operation: "introspect", params: { query: "operations", name: "edit_element" } }

Get detailed diagnostic information about the OAuth helper process.

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

Manage individual elements between your local portfolio and GitHub repository.

Check the status of your GitHub portfolio repository.

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 and enables resumption.

Reload elements of a specific type from the filesystem

Render a template element with provided variables

Search across all available sources (local portfolio, GitHub portfolio, and collection) for elements.

Search for elements that can handle a specific action verb (e.g., 'analyze', 'create', 'debug').

Search for content in the collection by keywords.

Enhanced search for collection content with pagination, filtering, and sorting.

Search your local portfolio by content name, metadata, keywords, tags, or description.

Set your username for persona attribution and collection participation

Set up GitHub authentication to access all DollhouseMCP features.

Submit a single element TO the DollhouseMCP community collection.

Sync ALL elements in your local portfolio with your GitHub repository.

Validate an element for correctness and best practices