MIND

Quill forms at m-i-n-d.ai/#/forms — public lead-capture forms that can auto-create CRM contacts / Life items. Actions: list, get, create, update, delete, submissions, public_get (read a published form by its public slug, no auth needed).

Fetch the full augmented markdown for one MIND Front Layer template. Returns a self-contained spec — when to create a document of this type, what slots to fill, and how to store the filled copy. Always read the template before writing a typed document.

Get MIND knowledge graph statistics and diagnostics — entity/relationship counts, growth, label breakdown, and health status. Use this for a quantitative pulse-check on the graph itself (e.g. before a large ingestion, or to cite "MIND has N entities"); it does not search or retrieve content, so for facts, people or history use mind_query instead. Actions: stats (default overview), diagnostics (health check), labels (entity type breakdown). A low or zero count can mean an empty tenant OR a scoping/auth issue reading the wrong account — verify with mind_query on a known fact before treating a sm…

Read what MIND's Autonomous Learning Engine has already noticed about the user without being asked — patterns, weekly summaries, and proactive intelligence generated in the background — or trigger a fresh analysis pass on demand. Reach for this when the user asks "what have you noticed" or "anything I'm missing"; reach for mind_query when you already know what you're looking for. Actions: list (recent insights), unread_count, view (read one, marks it seen), feedback (rate helpful/not_helpful — tunes future insights), analyze (trigger a new pass now), weekly_summary, context (raw ALE state). 'N…

Invoice Agent at m-i-n-d.ai/#/invoiceagent. Actions: list, get, create, update, delete, ask (ask a question about an invoice), invite (⚠️ OUTWARD — emails the bill-to party a payment link; confirm with the user before calling), pdf_url (returns a PDF link string, no binary transferred through MCP), received (invoices billed to you).

MIND Library — personal bookshelf at m-i-n-d.ai/#/library. Actions: authors (author stats), books_list, book_get, book_content (chapter text/table of contents), book_companion (AI reading companion for a book), book_create, book_update, book_delete.

Manage Focus → Project → Outcome hierarchy + calendar in MIND Life. Items are either projects (top-level domain/client buckets that live inside a Focus) or outcomes (deliverables that live under a parent project). Use `item_type` + `parent_id` + `focus_id` on create/update to wire the hierarchy. Use list filters (item_type, parent_id, focus_id, top_level_only) to slice the board. Share a project with another MIND account using share/list_shares/revoke_share (requires LIFE_SHARING_ENABLED on the backend; grantee gets the project + its outcomes on their board).

List the 16 MIND Front Layer template types (SOUL, IDENTITY, BELIEFS, USER, AGENTS, TOOLS, SENSES, SKILLS, BEHAVIOR, LESSON, DECISION, POLICY, WORKFLOW, PREFERENCE, GOAL, RELATIONSHIP). Use this first to see what typed documents an agent can fill in. Each entry includes a short description and the source_tag used when storing filled documents.

MIND Mind Map — visual mind-mapping canvases at m-i-n-d.ai/#/mind-map. Actions: list, get, create, update, delete, get_shared (read a publicly shared map, no auth needed). Sharing, collaborators and AI generation from a prompt or project stay in the web app at m-i-n-d.ai/#/mind-map.

MoneyMIND — personal finance at m-i-n-d.ai/#/moneyMIND: accounts, transactions, categories, budgets, recurring bills, net worth, goals, credit, alerts, bill negotiation, bank statements. Actions: overview, accounts_list, account_create, account_update, account_delete, transactions_list, transaction_create, transaction_update, transaction_split, spending_summary, categories_list, category_create, rules_list, rule_create, rule_delete, budgets_list, budget_set, budget_delete, recurring_list, recurring_update, recurring_cancel, networth, networth_manual, networth_snapshot, goals_list, goal_create,…

Read and manage the user's MIND notification inbox — alerts, reminders, insight pings, and system messages generated by other MIND features. It is not a way to send a notification yourself. Use this to check what MIND has already surfaced to the user, or to clear it down; for the underlying event (why an insight fired, what an alert refers to) follow up with the originating tool (mind_insights, mind_sense, etc.) or mind_query. Actions: list, mark_read, mark_all_read, stats (total/unread/read counts). 'No notifications' or unread:0 means nothing has been pushed to the inbox — a quiet inbox and …

Operate Ozzie — the autonomous OSINT analyst — through MIND. Investigate a target (domain, IP, org, person) and get a cited intelligence dossier; or set up live-feed alerts and watchlists in plain English. Ozzie's dossiers and alerts persist in its MIND knowledge graph, so use mind_query to recall past intelligence and mind_osint to run new work.

Influencer Factory Command Center — synthetic-persona creators that publish across Blotato platforms. Admin-only. Phase 1 surface: persona CRUD (auto-creates a Featured MIND row with IF fields), face anchor (AI-generate via Nano Banana Pro OR user-uploaded with rights affirmation), face variants (image-to-image via n8n + Fal.ai, always pinned to anchor — never chained), voice (ElevenLabs library search + clone + sample), per-platform bios (with optional LLM draft), Blotato account registration (YouTube/IG/LinkedIn/X/Threads/Pinterest; TikTok marked manual_upload). Each persona is publicly chat…

Manage the user's own MIND profile, public-chat prompt, and model preferences — bio, display name, the system prompt used at their public /m/{username} chat surface, and their default LLM model. This is account/identity settings, not knowledge-graph content — for what MIND knows about the user, use mind_context or mind_query instead. Actions: get/update (profile fields), get_chat_prompt/set_chat_prompt, get_thought_prompt/set_thought_prompt, get_model/set_model/list_models. 'No custom prompt set' on get_chat_prompt/get_thought_prompt means the platform default applies, not that chat is unconfi…

Search the user's MIND knowledge graph — their persistent memory of people, projects, decisions, outcomes and history. Returns RETRIEVED CONTEXT for YOU to read and synthesize — documents, entries, entities and relationships — NOT a finished answer. Does not use MIND's LLM and costs 0 credits. Call this before asserting anything about the user's world, and before saying something does not exist. (Pass retrieve_only=false to have MIND's own LLM write the answer instead, which spends credits.) HOW TO ASK — this changes answer quality more than any parameter. Ask a rich, specific, full-sentence …

Store and manage content in your MIND knowledge graph. Use for facts, decisions, learnings, research, notes — anything worth remembering. Auto-categorized. Always log outcomes here after completing tasks. Supports create (default), delete, search, get, and list. ⚠️ PRIVATE vs PUBLIC: `document` and `entry` are PRIVATE to the user's knowledge graph. `feed_post` is a PUBLIC social-media post that appears on the user's public feed for everyone to see. Default to `entry` for all agent outcomes, logs, decisions, and research. NEVER use `feed_post` unless the user explicitly says "post", "share", "…

Launch and track autonomous deep-research jobs — MIND gathers sources, synthesizes them, and writes findings into the knowledge graph as it goes. Use this for a genuinely open-ended investigation (competitive analysis, market research, a technical deep-dive) that would take multiple search rounds; use mind_query for a quick fact lookup instead. Actions: start (launch, returns job_id), status (poll progress and read the summary once complete), list (all jobs). A job still 'running' has no findings yet — poll status again rather than treating a thin or missing summary as a negative result; once …

Save a filled-out Front Layer document with the proper type tag so retrieval can filter by it later. Wraps mind document creation and pre-bakes the source tag (`front-layer-<type>`). Use this — not raw mind_remember — for any SOUL/IDENTITY/BELIEFS/USER/BEHAVIOR/LESSON/POLICY/etc. document. Pass the markdown body (frontmatter + content) as the `content` field.

Access MINDsense — the user's live emotional state, signal history, spikes and emotionally-weighted entities, derived from valence/arousal signal processing rather than asked directly. Reach for this before a sensitive conversation, when deciding how hard to push on a topic, or when asked "how am I feeling" / "read the room"; reach for mind_query instead for factual history about what happened. Actions: state (current snapshot), signals (recent raw signals), timeline (historical trend), kg_weights (which entities carry emotional weight), spikes (notable events, some unacknowledged), acknowledg…

Log THIS agent's own live session into MIND Chat → Agents, so Anthony can read the transcript and reply — his reply reaches you on your next turn. Distinct from mind_remember (one durable fact) and mind_train (teaching the KG): this is the live, turn-by-turn session log, mirrored into a MIND document when you close it. PROTOCOL (do this every session): 1) CONNECT — as soon as mind_context succeeds, call action=open with source_key (your assigned MIND Chat toggle, e.g. "claude-code-1"), external_session_id (your runtime's own session id), runtime, title (first user ask, 6-10 words), machine/cw…

Create and manage share links for a MIND document. Actions: create (default — mint a new share link), list (this document's share links), list_all (every share link across your documents), revoke (delete one share link).

MIND Sheets — Airtable-style tables at m-i-n-d.ai/#/sheets. Actions: tables_list, table_create, table_update, table_delete, column_add, column_update, column_delete, columns_reorder, rows_list, row_create, row_update, row_delete, rows_bulk_delete, export_csv (returns raw CSV text).

MIND Sign — e-signature envelopes at m-i-n-d.ai/#/mindsign. Actions: list, get, create (JSON variant — document by pdf_url or pdf_base64), setup, fields, send (⚠️ OUTWARD — emails every signer; confirm with the user before calling), resend (⚠️ OUTWARD — re-emails one signer; confirm with the user before calling), void, delete, audit, certificate, download_url (returns a download link string, no binary transferred through MCP).

Interact with MIND's social layer — create thoughts (PUBLIC feed posts), browse the feed, manage communities, and engage with other users' content. ⚠️ create_thought posts to the user's PUBLIC social feed for everyone to see — NEVER call unless the user explicitly said "post", "share", "tweet", "feed", or "thought to my feed". For private agent outcomes, deploy logs, or work updates, use mind_remember with type=entry instead.

Read social media analytics from MIND's Social Dashboard — YouTube/LinkedIn/X/Twitch channel stats, recent videos with performance, retention curves, traffic sources, comment sentiment, and goal progress. Use this to answer questions like 'how did Tuesday's video do?' or 'am I on pace for 1k subs?'

Manage site-wide tasks — assignable, completable work items that are lighter-weight than a Life project/outcome and simpler than a Kanon checklist item. Reach for mind_tasks for a single actionable to-do (optionally attached to a Life project via parent_type=life_item, a CRM contact via parent_type=contact, or an agent) that needs an owner and a done/not-done state; reach for mind_life when the work is itself a deliverable inside the Focus→Project→Outcome hierarchy, and mind_checklists when you need a multi-item checklist with a progress rollup. Assign tasks to a MIND member, an agent, or an e…

Agent ticket queue — file, view, answer, triage, and resolve tickets on any agent in the Command Center. A ticket is client feedback / critique / an idea / a feature request / a bug. Every ticket lives on an agent (agent_slug is always required) and auto-assigns to the Ernie triage agent. Use action=create to file one, action=comment to answer a thread, action=update or action=resolve to triage. Backed by /admin/agents/{slug}/tickets; admin API key required.

Tempo time tracking. Actions: start, stop, current (the running entry, if any), entries_list, entry_create (manual entry), entry_update, entry_delete, summary.

Operate TraderMIND — the agentic trading engine. Use whenever the user asks about markets, the trader, a MIND Vision forecast, their trading journal, or wants to react to a trade idea. Read the engine: feed (live trade-idea feed) · forecast_latest (latest MIND Vision cone for a symbol) · forecasts (recent forecast history incl. resolution — every hit and miss) · bar_scores (per-candle predicted-vs-actual for one resolved forecast_id) · candles (OHLCV) · cycles (engine cycle summaries: regime, ideas, lessons) · health (is the engine up) · calibration (published honesty curve) · ai_journal (the …

Run guided or freeform sessions that teach MIND about the user through conversation, or extract an existing chat transcript into the knowledge graph as durable memories — this is how unstructured conversation becomes queryable facts, distinct from mind_remember (one explicit fact) or mind_query (reading facts back). Actions: start (begin a session, optionally typed: basics/network/expertise/history/goals/freeform), chat (send the next training message), status (progress + items learned so far), list_sessions, pause/resume, save_chat (extract a chat session_id into the graph). 'Items learned: 0…