mcp-server: DollhouseMCP is an open-source platform that customizes AI through modular elements (personas, skills, templates, agents, memories, ensembles). It uses the MCP-AQL protocol with CRUDE endpoints and a Gatekeeper permission system for secure and flexible AI behavior modification. Installation is via npm or an interactive setup wizard, and it works across multiple platforms and MCP-compatible clients.; context-mode: Every tool call in an MCP (Model-Controller-Program) environment dumps raw data into the context window, quickly consuming space and causing the agent to lose track of ongoing tasks. Context Mode is an MCP server that tackles this by sandboxing tool outputs to significantly reduce context usage, tracking session events in SQLite for continuity, and promoting 'think in code' to minimize data processing within the LLM.
Activate a read-only analyst persona to safely browse and list elements
Deep repository research and analysis (e.g., architecture, contributors, issues)