{"report":{"v":1,"package":"@dollhousemcp/mcp-server","version":"2.0.43","ranAt":"2026-11-16T11:47:22.573Z","install":{"ok":true,"bin":"mcp-server","integrity":"sha512-v7S2QxVuvxtLaGkBKXO9gtjWuzMSdRHBJzl4d8DtVNXMD0DaaXBicuLDfhcODIoZEzh5pawjSllI8GMkqbTncw==","deps":249,"scripts":[],"bins":["dollhousemcp","mcp-server","dollhouse-console-token"],"license":"AGPL-3.0-or-later","engines":"node >=18.0.0","repository":"git+https://github.com/DollhouseMCP/mcp-server.git"},"start":{"ok":true,"ms":642,"serverName":"dollhousemcp","serverVersion":"2.0.43","protocol":"2025-06-18","stderr":"ng: NOUN_SUFFIX_PATTERN should not match 'document' but does\n[2026-11-16T11:47:35.995Z] [DEBUG] Regex pattern validation completed successfully\n[2026-11-16T11:47:35.995Z] [INFO] Loaded enhanced index configuration\n[2026-11-16T11:47:35.995Z] [DEBUG] ContextTracker initialized\n[2026-11-16T11:47:35.996Z] [DEBUG] EnhancedIndexManager initialized\n[2026-11-16T11:47:35.996Z] [DEBUG] Started automatic memory cleanup\n[2026-11-16T11:47:35.996Z] [INFO] MCP Interface Mode: mcpaql\n[2026-11-16T11:47:36.007Z] [INFO] Tool Registration Complete: 5 tools, ~4,704 tokens\n[2026-11-16T11:47:36.007Z] [INFO] Token Savings: 2,471 tokens saved (34.4%) vs discrete mode (42 tools, ~7,175 tokens)\n[2026-11-16T11:47:36.008Z] [INFO] [ResourceHandler] MCP Resources disabled (future-proof implementation, opt-in required)\n[2026-11-16T11:47:36.008Z] [DEBUG] Telemetry: Disabled via DOLLHOUSE_TELEMETRY environment variable\n[2026-11-16T11:47:36.009Z] [INFO] Portfolio and personas initialized successfully\n[2026-11-16T11:47:36.009Z] [INFO] DollhouseMCP server ready - waiting for MCP connection on stdio\n[2026-11-16T11:47:36.009Z] [DEBUG] DollhouseMCPServer.run() completed initialization\nDOLLHOUSEMCP_READY\n[FileLogSink] cleanup error: Error: ENOENT: no such file or directory, scandir '/tmp/.dollhouse/logs/'\n[FileLogSink] cleanupByFileCount error: Error: ENOENT: no such file or directory, scandir '/tmp/.dollhouse/logs/'\n\n  DollhouseMCP Management Console\n  http://dollhouse.localhost:41715\n  http://127.0.0.1:41715 (fallback)\n\n  Session token: /tmp/.dollhouse/run/console-token.auth.json\n\n  Type \"q\" or \"quit\" to exit.\n\n"},"tools":[{"name":"mcp_aql_create","description":"Additive, non-destructive operations.\n\nSupported operations: create_element, import_element, addEntry, verify_challenge, release_deadlock, beetlejuice_beetlejuice_beetlejuice, record_execution_step, install_collection_content, submit_collection_content, init_portfolio, sync_portfolio, portfolio_element_manager, setup_github_auth, configure_oauth, import_persona\n\nElement types: persona, skill, template, agent, memory, ensemble\n\nThese operations add new data without removing or overwriting existing content.\n\nQuick start examples:\n{ operation: \"create_element\", element_type: \"persona\", params: { element_name: \"MyPersona\", description: \"A helpful assistant\", instructions: \"You ARE a helpful assistant. ALWAYS provide clear, accurate responses.\" } }\n{ operation: \"create_element\", element_type: \"agent\", params: { element_name: \"MyAgent\", description: \"Task executor\", instructions: \"Execute goals methodically. Report progress at each step.\", goal: { template: \"Complete: {objective}\", parameters: [{ name: \"objective\", type: \"string\", required: true }] } } }\n{ operation: \"create_element\", element_type: \"memory\", params: { element_name: \"session-notes\", description: \"Session context and notes\" } }\n{ operation: \"create_element\", element_type: \"ensemble\", params: { element_name: \"my-ensemble\", description: \"Combined element set\", metadata: { elements: [{ element_name: \"expert\", element_type: \"persona\", role: \"primary\" }, { element_name: \"analysis\", element_type: \"skill\", role: \"support\" }] } } }\nValid ensemble roles: primary, support, override, monitor, core\n{ operation: \"addEntry\", params: { element_name: \"session-notes\", content: \"Remember this fact\", tags: [\"important\"] } }\nNote: addEntry content supports markdown (headers, lists, bold, tables, code blocks). Ensure markdown content is properly JSON-escaped — use \\n for newlines, \\\" for quotes, and \\\\ for backslashes within the JSON string value.\n\nExecution lifecycle — record agent progress (appends step records, like addEntry):\n{ operation: \"record_execution_step\", params: { element_name: \"code-reviewer\", stepDescription: \"Analyzed files\", outcome: \"success\", findings: \"Found 3 issues\" } }\nThis is the normal next lifecycle call after mcp_aql_execute { operation: \"execute_agent\", ... }.\nResponse flow: record_execution_step returns { autonomy: { continue, factors, notifications? } }. Check autonomy.continue to decide whether to proceed. Check autonomy.notifications for permission_pending (gatekeeper blocks), autonomy_pause, or danger_zone alerts to relay to human operators.\n\nImport & portfolio:\n{ operation: \"import_element\", element_type: \"skill\", params: { element_name: \"code-formatter\", data: \"...\" } }\n{ operation: \"import_persona\", params: { source: \"/path/to/persona.md\" } }\n{ operation: \"install_collection_content\", params: { element_type: \"persona\", element_name: \"Creative-Writer\" } }\n{ operation: \"submit_collection_content\", params: { element_type: \"skill\", element_name: \"code-formatter\" } }\n{ operatio","params":["operation","element_type","params","operations"]},{"name":"mcp_aql_read","description":"Safe, read-only operations.\n\nSupported operations: activate_element, open_portfolio_browser, open_logs, open_metrics, open_permissions, open_setup, permission_prompt, evaluate_permission, get_effective_cli_policies, get_permission_authority, get_pending_cli_approvals, search, list_elements, get_element, get_element_details, search_elements, query_elements, get_active_elements, validate_element, render, export_element, deactivate_element, introspect, get_capabilities, get_execution_state, get_gathered_data, 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, convert_skill_format, get_build_info, get_cache_budget_report, query_logs, query_metrics, find_similar_elements, get_element_relationships, search_by_verb, get_relationship_stats\n\nElement types: persona, skill, template, agent, memory, ensemble\n\nThese queries only read data and never modify server state.\n\nQuick start examples:\n{ operation: \"list_elements\", element_type: \"persona\" }\n{ operation: \"get_active_elements\", element_type: \"persona\" }\n{ operation: \"search_elements\", params: { query: \"creative\" } }\n{ operation: \"get_element\", element_type: \"memory\", params: { element_name: \"session-notes\" } }\n\nElement operations:\n{ operation: \"activate_element\", element_type: \"persona\", params: { element_name: \"Default\" } }\n{ operation: \"deactivate_element\", element_type: \"persona\", params: { element_name: \"Default\" } }\n{ operation: \"get_element_details\", element_type: \"skill\", params: { element_name: \"code-review\" } }\n{ operation: \"query_elements\", element_type: \"persona\", params: { filters: { category: \"creative\" } } }\n{ operation: \"validate_element\", element_type: \"agent\", params: { element_name: \"task-planner\" } }\n{ operation: \"render\", params: { element_name: \"meeting-notes\", variables: { date: \"2026-03-03\" } } }\n{ operation: \"export_element\", element_type: \"persona\", params: { element_name: \"Tech-Writer\" } }\n{ operation: \"open_portfolio_browser\" }\n{ operation: \"open_logs\" }\n{ operation: \"open_metrics\" }\n{ operation: \"open_permissions\" }\n{ operation: \"open_setup\" }\n\nMemory-specific search (filter by tags):\n{ operation: \"search\", params: { query: \"*\", type: \"memory\", filters: { tags: [\"important\"] } } }\n\nExecution lifecycle — read-only queries:\n{ operation: \"get_execution_state\", params: { element_name: \"code-reviewer\" } }\n{ operation: \"get_gathered_data\", params: { element_name: \"code-reviewer\", goalId: \"goal-id\" } }\nFor execution-state reads, reuse the same element_name you passed to execute_agent. If element_name is missing, retry with the same agent name rather than inventing a new one.\n\nCollection:\n{ operation: \"browse_collection\", params: { section: \"personas\" } }\n{ operation: \"search_collection\", params: { query: \"creative\" } }\n{ operation: \"search_collection_enhanced\", params: { query: \"creative\", page: ","params":["operation","element_type","params","operations"]},{"name":"mcp_aql_update","description":"Modifying operations that overwrite data.\n\nSupported operations: edit_element, upgrade_element\n\nElement types: persona, skill, template, agent, memory, ensemble\n\nThese operations modify existing data, potentially overwriting previous values.\n\nNote: Memories are append-only and do not support edit_element. Use addEntry (CREATE) to add new entries.\n\nQuick start example:\n{ operation: \"edit_element\", element_type: \"persona\", params: { element_name: \"MyPersona\", input: { description: \"Updated description\" } } }\n{ operation: \"edit_element\", element_type: \"persona\", params: { element_name: \"Friendly-Teacher\", input: { instructions: \"Updated behavioral directives.\" } } }\n{ operation: \"edit_element\", element_type: \"agent\", params: { element_name: \"code-reviewer\", input: { instructions: \"Updated agent behavioral profile.\", goal: { template: \"Complete: {task}\" } } } }\n{ operation: \"upgrade_element\", element_type: \"agent\", params: { element_name: \"task-planner\" } }\n\nDiscover required parameters — use mcp_aql_read:\n{ operation: \"introspect\", params: { query: \"operations\", name: \"edit_element\" } }","params":["operation","element_type","params","operations"]},{"name":"mcp_aql_delete","description":"Destructive operations that remove data.\n\nSupported operations: delete_element, clear, clear_github_auth\n\nElement types: persona, skill, template, agent, memory, ensemble\n\nThese operations remove data. Use with caution.\n\n⚠️ 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 protection against unintended data loss.\n\nQuick start examples:\n{ operation: \"delete_element\", element_type: \"persona\", params: { element_name: \"Old-Persona\" } }\n{ operation: \"clear\", params: { element_name: \"temp-notes\" } }\n{ operation: \"clear_github_auth\" }\n\nDiscover required parameters — use mcp_aql_read:\n{ operation: \"introspect\", params: { query: \"operations\", name: \"delete_element\" } }","params":["operation","element_type","params","operations"]},{"name":"mcp_aql_execute","description":"Execution lifecycle operations for executable elements (agents, workflows, pipelines).\n\nSupported operations: confirm_operation, approve_cli_permission, execute_agent, complete_execution, continue_execution, abort_execution, prepare_handoff, resume_from_handoff\n\nThese operations manage runtime execution state. Unlike CRUD operations (which manage definitions), Execute operations handle the execution lifecycle:\n- execute_agent: Start a new execution (returns goalId and stateVersion for tracking)\n- complete_execution: Signal successful completion once the goal is done\n- continue_execution: Resume a previously paused execution with the same goal parameters\n- abort_execution: Abort a running execution, rejecting further operations\n- confirm_operation: Confirm a pending operation that requires user approval (Gatekeeper flow)\n- approve_cli_permission: Approve a pending CLI tool permission request\n- prepare_handoff: Serialize goal progress into a portable handoff block for session transfer\n- resume_from_handoff: Resume agent execution from a handoff block with integrity validation\n\nIMPORTANT: Execute operations are potentially destructive (agents can perform any action) and non-idempotent (calling execute_agent twice creates two separate executions).\n\n⚠️ SECURITY: Do not auto-allow this endpoint in your host settings (e.g., Claude Code settings.json). Each execution should require explicit human approval. Auto-allowing bypasses the per-operation confirmation gate. While DangerZone verification and element deny policies still provide protection, the primary human review checkpoint is lost.\n\nCanonical loop:\n1. Call execute_agent once to start the goal and receive { goalId, stateVersion, activeElements, safetyTier, ... }.\n2. After each chunk of work, use mcp_aql_create: { operation: \"record_execution_step\", ... }.\n3. Read record_execution_step.autonomy.continue and any autonomy.notifications to decide whether to continue, pause for a human, or handle a gatekeeper block.\n4. When the goal is finished, call complete_execution.\nUse continue_execution only when an already-started goal was paused and you are resuming it with the same goal parameters. It is not the normal next call after execute_agent.\n\nQuick start examples:\n{ operation: \"execute_agent\", params: { element_name: \"code-reviewer\", parameters: { objective: \"Review code\" } } }\nNext lifecycle step — use mcp_aql_create:\n{ operation: \"record_execution_step\", params: { element_name: \"code-reviewer\", stepDescription: \"Reviewed auth module\", outcome: \"success\", findings: \"Found 2 security issues\" } }\n{ operation: \"complete_execution\", params: { element_name: \"code-reviewer\", outcome: \"success\", summary: \"Completed review\" } }\n{ operation: \"abort_execution\", params: { element_name: \"data-collector\", reason: \"User requested cancellation\" } }\n{ operation: \"continue_execution\", params: { element_name: \"rubric-qa-agent\", previousStepResult: \"Verified citation set\", parameters: { run_dir: \"/app/run\", deliverable_","params":["operation","element_type","params","operations"]}],"toolsHash":"168e9170050f2919015d83c504861f3c529362c7d28510793ce191bf543e9c53","wrote":["/tmp/.dollhouse/run/permission-server-96.port","/tmp/.dollhouse/run/permission-server.port","/tmp/.dollhouse/run/console-token.auth.json","/tmp/.dollhouse/run/console-leader.auth.lock","/tmp/.dollhouse/hooks/pretooluse-vscode.sh","/tmp/.dollhouse/hooks/permission-port-discovery.sh","/tmp/.dollhouse/hooks/permission-hook-config.sh","/tmp/.dollhouse/hooks/pretooluse-cursor.sh","/tmp/.dollhouse/hooks/pretooluse-codex.sh","/tmp/.dollhouse/hooks/pretooluse-dollhouse.sh","/tmp/.dollhouse/hooks/pretooluse-windsurf.sh","/tmp/.dollhouse/hooks/pretooluse-gemini.sh","/tmp/.dollhouse/config.yml","/tmp/.dollhouse/cache/collection-cache.json","/tmp/.dollhouse/portfolio/templates/security-vulnerability-report.md","/tmp/.dollhouse/portfolio/templates/code-documentation.md","/tmp/.dollhouse/portfolio/templates/executive-report.md","/tmp/.dollhouse/portfolio/templates/threat-assessment-report.md","/tmp/.dollhouse/portfolio/templates/penetration-test-report.md","/tmp/.dollhouse/portfolio/templates/professional-email.md","/tmp/.dollhouse/portfolio/templates/project-brief.md","/tmp/.dollhouse/portfolio/templates/meeting-notes.md","/tmp/.dollhouse/portfolio/skills/penetration-testing.md","/tmp/.dollhouse/portfolio/skills/data-analysis.md","/tmp/.dollhouse/portfolio/skills/research.md","/tmp/.dollhouse/portfolio/skills/code-review.md","/tmp/.dollhouse/portfolio/skills/translation.md","/tmp/.dollhouse/portfolio/skills/threat-modeling.md","/tmp/.dollhouse/portfolio/skills/creative-writing.md","/tmp/.dollhouse/portfolio/skills/research-to-elements.md","/tmp/.dollhouse/portfolio/ensembles/development-team.md","/tmp/.dollhouse/portfolio/ensembles/business-advisor.md","/tmp/.dollhouse/portfolio/ensembles/creative-studio.md","/tmp/.dollhouse/portfolio/ensembles/dollhouse-expert-suite.md","/tmp/.dollhouse/portfolio/ensembles/security-analysis-team.md","/tmp/.dollhouse/portfolio/ensembles/welcome-to-the-dollhouse.md","/tmp/.dollhouse/portfolio/memories/_index.json","/tmp/.dollhouse/portfolio/memories/project-context.md","/tmp/.dollhouse/portfolio/memories/conversation-history.md","/tmp/.dollhouse/portfolio/memories/system/dollhousemcp-baseline-knowledge.yaml"],"host":{"commit":"eaaffffaf52255d1b77dc4aacffdfaf353f0c12c","run":"https://github.com/itsHaddad/bragproof/actions/runs/43857070216"},"network":{"names":["registry.npmjs.org"],"conns":[]}},"summary":{"outcome":"started","needs":[],"contacts":[],"flags":[{"kind":"orders","tool":"mcp_aql_create","quote":"ful assistant\", instructions: \"You ARE a helpful assistant. ALWAYS provide clear, accurate responses.\" } } { operation: \"create_element\", element_type: \"agent\", param"},{"kind":"very-long","tool":"mcp_aql_create","quote":"3000 characters or more"},{"kind":"very-long","tool":"mcp_aql_read","quote":"3000 characters or more"},{"kind":"orders","tool":"mcp_aql_execute","quote":"t execution from a handoff block with integrity validation IMPORTANT: Execute operations are potentially destructive (agents can perform any action) and non-idempotent"},{"kind":"very-long","tool":"mcp_aql_execute","quote":"3000 characters or more"}],"tools":5,"wrote":40,"callsTried":0,"callsAnswered":0,"callContacts":[]},"history":[{"package":"@dollhousemcp/mcp-server","version":"2.0.43","ranAt":"2026-11-16T11:47:22.573Z","outcome":"started","tools":5,"contacts":0,"flags":5,"serious":0,"toolsHash":"168e9170050f2919015d83c504861f3c529362c7d28510793ce191bf543e9c53"}],"page":"https://bragproof.smaverk.com/r/%40dollhousemcp/mcp-server"}