MIND MCP server

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

• mind_accounts

  Manage multi-MIND accounts. A 'MIND' is a knowledge-graph account; one person can own or be granted access to many. Use to discover every MIND you can access (list), spin up a new one (create), permanently delete one (delete), see who can access a MIND (members), grant an existing user access (grant), email an invitation (invite), or switch into a granted MIND (switch — POST /developer/v1/accounts

• mind_admin

  Admin-only tool for managing MIND users and the Featured Minds Portal. Requires an admin API key. Full CRUD over featured minds (create / list / get_full / update / update_owner_profile / reorder / delete), plus user provisioning and tier/credit management. The Featured Minds Portal at /admin/featuredmindsportal uses these same endpoints — get_featured_mind_full + update_featured_mind_owner_profil

• mind_agents

  Admin-only Agent Command Center — canonical registry of every Astra AI agent (running on VPS, planned, archived). Query before scaffolding a new agent. Update status / current_job / responsibilities after non-trivial work. Every agent is owned by a MIND account (owner_username) and can be transferred or shared with other accounts as owner/viewer. Backed by /admin/agents on the MIND backend; admin

• mind_automatewrite action

  Create and manage MIND-native automations — scheduled or event-triggered rules that run without a human or agent invoking them each time (e.g. a weekly CRM digest, a webhook that logs an event to a life project). This is for recurring MIND-internal work, not a general task scheduler for external systems. Actions: list/create/update/delete, run_now (fire immediately for testing), history (execution

• mind_books

  MIND Books — small-business accounting at m-i-n-d.ai/#/mind-books. Actions: overview, vendors_list, vendor_create, customers_list, customer_create, accounts, bills, invoices, health.

• mind_bootstrap_templates

  Seed all 16 MIND Front Layer templates into this MIND tenant as system documents. After running, the templates become queryable through mind_query so agents can ask 'what should I fill out for SOUL?' and retrieve the spec from their own knowledge graph. Idempotent — re-runs create fresh copies. Run once per new tenant.

• mind_budget

  MIND Budget — 13-week cash-flow planner at m-i-n-d.ai/#/budget. Actions: overview, set_cells, set_starting, set_rows, row_create, row_update, row_delete, rows_reorder, row_cancel, row_restore, set_goals, set_quarter, variance, roll_forward, autofill_from_statement, autofill_accept, build_from_statements, build_accept, automanage_health.

• mind_checklists

  Kanon checklists at kanon.theastraway.com, attached to Life items or tasks. Actions: templates_list, template_get, template_create, template_update, template_delete, list, get, create, update, delete, toggle_item, complete, progress (rollup for a parent_type+parent_id).

• mind_context

  Load the user's persistent context from MIND at session start — identity, preferences, operating rules, current priorities and recent activity. Returns RETRIEVED CONTEXT for YOU to synthesize, NOT a finished briefing. Does not use MIND's LLM and costs 0 credits. Call this at the start of every session. Pass only the `sections` you actually need for the task at hand — a focused payload measurably o

• mind_crm

  Manage contacts and relationships in MIND CRM — the system of record for people, companies, leads and prospects, separate from the knowledge graph's document/entry memory. Reach for this (not mind_query) when you need to create, update, or list a specific contact record, or log/read a dated interaction history — reach for mind_query when you want a synthesized answer about a relationship drawn fro

• mind_emailwrite action

  MIND Email Manager at m-i-n-d.ai/#/email. Actions: status, inbox, thread, message, search, sync, action (archive/trash/mark_read/mark_unread/star/unstar a batch of messages), draft (AI-draft a reply or new email, no send), draft_save, send (⚠️ OUTWARD — sends a real email; confirm with the user before calling), voice, voice_pref_set, voice_pref_clear, voice_rebuild. Note: the REST body field 'acti

• mind_focuses

  Manage Focuses — the top-level buckets that group Life Projects. Every project lives inside one focus (or 'No Focus'). Use list to see all focuses + their project counts, create to add a new bucket (e.g. 'Astra', 'Atlas', 'Fundraising'), update/delete to maintain them. Pass the returned focus_id to mind_life when creating projects.

• mind_folder_routes

  Configure deterministic system-folder routing — which folder each kind of system-generated doc (life items, CRM, chat saves, tasks, training, reasoning trajectories, playbooks, trader signals, cloud imports) is filed into automatically. Actions: list, set, clear, apply_recommended (idempotent one-tap setup that creates Life/CRM/Chats/Reasoning/Trader folders and wires every source_type to its dest

• mind_folder_suggest

  Ask MIND which folder a piece of content belongs in. Reads every folder's routing_hint (set via mind_folders set_hint) and uses a cheap LLM to pick the best match. Returns folder_id=null when no folder's hint clearly applies — in that case leave the doc unfiled rather than guess. Typical agent flow: suggest → mind_remember (create the doc) → mind_folders move_documents (file it to the suggested fo

• mind_folders

  Organize your MIND documents into folders. Folders are a presentation layer — the knowledge graph still indexes and retrieves across every document regardless of folder. Use mind_remember to create a document, then mind_folders move_documents to file it. Actions: list, create, rename, move, delete, move_documents, set_hint, secure, unsecure, unlock, reset_request, reset (Secure Folders — password-

• mind_forms

  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).

• mind_get_template

  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.

• mind_graph

  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 (hea

• mind_insights

  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 (re

• mind_invoices

  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

  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.

• mind_life

  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 w

• mind_list_templates

  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_mindmap

  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.

• mind_moneymind

  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, r

• mind_notify

  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, mi

• mind_osint

  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.

• mind_personas

  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 s

• mind_profile

  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_p

• mind_query

  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. (

• mind_remember

  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 ap

• mind_research

  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

• mind_save_typed

  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.

• mind_sense

  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. Ac

• mind_sessions

  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.

• mind_sharewrite action

  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

  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

  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 bi

• mind_social

  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_reme

• mind_social_analytics

  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?'

• mind_tasks

  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 wo

• mind_tickets

  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. B

• mind_timer

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

• mind_trader

  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.

• mind_trainwrite action

  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/histor

• Code scan15 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 2 days ago15/15
• Maintainer identityregistry namespace matches repository owner6/10

Safety score

80/100

higher than 69% of 876 Sales and outbound servers

Tools

45

the typical Sales and outbound server has 8

Tools that change things

9%

typical: 11%. Fewer write tools means less an agent can break

GitHub stars

6

more than 88% of 420 Sales and outbound servers

Downloads a week

142

more than 70% of 156 Sales and outbound servers with a package

MIND: common questions

Is MIND MCP server safe?

Mostly: it is graded B (80/100). Read the MIND safety report

How do I install MIND?

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

Does MIND need an API key?

Yes. The registry entry asks for MIND_API_KEY.

Is MIND maintained?

The last commit was 34 days ago (2026-10-01). The latest release is v0.29.2.

What can I use instead of MIND?

Servers from other publishers that do the same job: OpenLeads MCP server, Pinlyx MCP server and Cargo MCP server. Compare all MIND alternatives.

How does MIND compare with other Sales and outbound MCP servers?

safety score 80/100 (higher than 69% of 876 Sales and outbound servers); tools 45 (the typical Sales and outbound server has 8); tools that change things 9% (typical: 11%. Fewer write tools means less an agent can break). Full comparison.