@astramindapp/mcp-server

@astramindapp/mcp-server

MIND MCP Server — The most complete AI memory layer available. 24 tools, 147 actions.

Your AI agents forget everything between sessions. MIND fixes that. Connect any MCP-compatible agent to your personal knowledge graph — with emotional intelligence, CRM, life management, site-wide assignable tasks, social features, self-training, autonomous insights, an admin-only Agent Command Center with per-agent ticket queues, an admin-only Featured Minds Portal (curate the public marketplace at m-i-n-d.ai from any MCP client — model, public chat prompt, temperature, brand fields, write-through to the linked user's profile), and more.

Self-describing. Every connecting client receives a full integration briefing in the MCP initialize response, and can read the complete playbook from the mind://integration-guide resource — so any agent knows what MIND is, which integration path fits its runtime (MCP server / OpenClaw plugin / REST API), how to authenticate, and the session protocol, without being told.

24 Tools

Tool	Actions	What It Does
mind_query	1	Semantic search across your knowledge graph (5 search modes)
mind_remember	5	Store, search, get, list, delete — documents, entries, thoughts
mind_folders	6	Organize documents into folders — list, create, rename, move, delete, file documents
mind_context	1	Load persistent identity, preferences, rules, priorities, recent activity
mind_life	13	Goals, projects, tasks + full calendar management + productivity stats
mind_crm	7	Contacts, pipeline, activity logging, interaction history
mind_tasks	9	Site-wide tasks — assignable, completable work items on projects, contacts, or agents, plus completion reports
mind_graph	3	Graph stats, diagnostics, entity labels
mind_admin	11	Admin-only. User provisioning + the Featured Minds Portal: full CRUD over the public marketplace (get_full / update / update_owner_profile / reorder / delete), tier/credit management
mind_sense	7	MINDsense emotional intelligence — state, signals, timeline, KG weights, spikes
mind_research	3	Launch autonomous deep research jobs
mind_train	7	Self-training sessions + save chats to knowledge graph
mind_social	14	Thoughts (posts), social feed, communities, likes, comments
mind_profile	9	Profile, custom system prompts, LLM model selection
mind_insights	7	Autonomous Learning Engine insights, weekly summaries, feedback
mind_automate	6	Scheduled automations, event triggers, execution history
mind_notify	4	Notifications, mark read, stats
mind_agents	21	Admin-only. Agent Command Center — list/search/get/create/update/delete agents, heartbeats, probes, activity log, import from MIND, seed canonical fleet, link invoices, transfer ownership + share agents with other accounts
mind_tickets	7	Admin-only. Agent ticket queue — file, view, answer (comment), triage, resolve, and delete client feedback / bugs / ideas on any agent
mind_accounts	6	Multi-MIND accounts — list MINDs you can access, create new ones, delete MINDs you own, manage owners/viewers, send email invitations
mind_list_templates	1	List the 16 Front Layer typed-document templates
mind_get_template	1	Fetch the full spec for one Front Layer template
mind_save_typed	1	Save a filled-out Front Layer document with its type tag
mind_bootstrap_templates	1	Seed all 16 Front Layer templates into a MIND tenant

Quick Start

1. Get a MIND API Key

Sign up at m-i-n-d.ai → Settings → Developer → Create API Key

2. Install

npm install -g @astramindapp/mcp-server

3. Configure Your AI Tool

Claude Code

claude mcp add mind -- env MIND_API_KEY=mind_xxx mind-mcp

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "mind": {
      "command": "mind-mcp",
      "env": {
        "MIND_API_KEY": "mind_your_key_here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "mind": {
      "command": "mind-mcp",
      "env": {
        "MIND_API_KEY": "mind_your_key_here"
      }
    }
  }
}

Any MCP-Compatible Agent

The server works with any tool that supports Model Context Protocol — Claude, GPT, Gemini, Llama, or any future model.

How It Works

Your AI Agent  <-->  MCP Protocol  <-->  MIND MCP Server  <-->  Personal Knowledge Graph
                                                                  |
                                                           Emotional Intelligence
                                                           Autonomous Learning
                                                           CRM + Life + Social

• Agent calls mind_context at session start → loads identity, rules, priorities
• Agent calls mind_query before decisions → retrieves relevant memories
• Agent calls mind_remember after tasks → stores outcomes and learnings
• Agent calls mind_sense → reads user's emotional state to adapt responses
• Agent calls mind_insights → surfaces autonomous pattern detection
• Next session, any agent has full context. Knowledge compounds.

What Makes MIND Different

vs. Flat File Memory (MEMORY.md)

	Flat Files	MIND
Size	~20K chars, truncated	Unlimited knowledge graph
Retrieval	Loads everything every turn	Only relevant memories via semantic search
Structure	Unstructured text	Graph with entities, relationships, and emotional weights
Cross-agent	One tool only	Shared across all AI agents
Intelligence	None	Autonomous pattern detection + emotional encoding

vs. Other MCP Memory Servers

	Anthropic Official	Mem0	Graphiti/Zep	MIND
Tools	8	4	9	24
Knowledge graph	Basic (JSON)	No (vectors)	Yes (Neo4j)	Yes (per-user MIND graph)
Emotional intelligence	No	No	No	Yes (patent-pending)
CRM	No	No	No	Yes
Life management	No	No	No	Yes
Social features	No	No	No	Yes
Self-training	No	No	No	Yes
Research agent	No	No	No	Yes
Automations	No	No	No	Yes
Mobile app	No	No	No	Yes

Tool Reference

mind_query — Search Your Knowledge Graph

query: "What did I decide about the authentication approach?"
mode: "hybrid"  // hybrid (default), mix, global, local, naive

Returns an AI-synthesized answer from your stored documents, entries, and thoughts with source attribution.

mind_remember — Store & Manage Content

Action	Description
create	Store content (auto-categorized as document, entry, or thought)
delete	Remove by ID
search	Find entries/thoughts by query
get	Retrieve specific item by ID
list	Paginated listing of all content

mind_folders — Organize Documents into Folders

Folders are a presentation layer over the document tray — the knowledge graph still indexes and retrieves across every document regardless of folder.

Action	Description
list	All folders, each with its document count
create	Create a folder (optionally nested under a parent)
rename	Change a folder's name
move	Re-nest a folder under a different parent
delete	Remove a folder — its documents and subfolders move up a level; nothing is deleted
move_documents	File one or more documents into a folder

mind_context — Load Persistent Context

Loads five structured sections at session start:

• Soul — Core identity, mission, personality
• User — Who the user is, their role, preferences
• Rules — Operating constraints, behavioral guidelines
• Priorities — Current goals, active projects, deadlines
• Recent — Latest activity, outcomes, decisions

mind_life — Life Management + Calendar

Action	Description
list, create, update, complete, delete, move, get	Full task/goal CRUD
bulk_delete	Delete up to 200 life items in one call (item_ids array)
calendar_list, calendar_create, calendar_update, calendar_delete	Calendar events
stats	Productivity metrics and completion rates

mind_crm — Contact Relationship Management

Action	Description
list, create, update, delete, get	Contact CRUD with pipeline stages
log_activity	Record calls, emails, meetings, notes
list_activities	View interaction history

mind_tasks — Site-Wide Tasks

Assignable, completable, reportable work items. A task can attach to a Life project (parent_type: "life_item"), a CRM contact ("contact"), an agent ("agent"), or stand alone. Assign tasks to a MIND member, an agent, or an external email address.

Action	Description
list	List/filter tasks by status, priority, parent, assignee, or overdue
create	Create a task — attach to a project/contact/agent, assign, set a due date
get, update, delete	Task CRUD
complete, reopen	Mark a task done or reopen it
assign	(Re)assign to a member/agent/external; optionally fire the agent
reports	Completion analytics — counts, overdue, by-assignee, 8-week throughput

mind_tasks({ action: "create", title: "Follow up with Acme",
             parent_type: "contact", parent_id: "<contact_id>",
             assignee_type: "agent", assignee_id: "fundraising-agent",
             dispatch_agent: true, due_date: "2026-06-01" })

mind_tasks({ action: "reports" })

mind_sense — MINDsense Emotional Intelligence

Action	Description
state	Current emotional state (valence, arousal, trend, sensitivity)
signals	Recent emotional signals with strength and source
timeline	Historical emotional data
kg_weights	Entities weighted by emotional significance
spikes	Detected emotional spikes
acknowledge	Mark a spike as acknowledged
summary	AI-generated emotional summary

mind_research — Autonomous Research

Action	Description
start	Launch a deep research job on any topic
status	Check job progress
list	View all research jobs

mind_train — Self-Training

Action	Description
start	Begin guided training (basics, network, expertise, history, goals, freeform)
chat	Send training message
status, list_sessions, pause, resume	Session management
save_chat	Save any chat conversation into the knowledge graph

mind_social — Social Layer

Action	Description
create_thought, get_thought, delete_thought, like_thought	Thought (post) management
feed, user_feed, search_feed	Social feed browsing
create_community, list_communities, get_community	Community management
join_community, leave_community	Membership
create_post, list_posts	Community posts

mind_profile — Profile & Preferences

Action	Description
get, update	Profile management
get_chat_prompt, set_chat_prompt	Custom chat system prompt
get_thought_prompt, set_thought_prompt	Custom thought generation prompt
get_model, set_model, list_models	LLM model selection (50+ models)

mind_insights — Autonomous Learning Engine

Action	Description
list	Recent pattern-detected insights
unread_count	Count of unseen insights
view, feedback	Mark seen, rate helpfulness
analyze	Trigger on-demand analysis
weekly_summary	Weekly intelligence summary
context	ALE context data

mind_automate — Automations

Action	Description
list, create, update, delete	Automation CRUD
run_now	Trigger immediately
history	Execution log

mind_notify — Notifications

Action	Description
list	View all notifications
mark_read, mark_all_read	Read management
stats	Notification overview

mind_admin — Administration & Featured Minds Portal

Requires an admin-scoped MIND API key. Powers everything at https://m-i-n-d.ai/#/admin/featuredmindsportal — the same surface any MCP client (Claude Code, Cursor, Windsurf, n8n via MCP, custom agents) can drive end-to-end.

User provisioning + tier/credits

Action	Description
create_user	Provision new MIND account; optionally generate an API key
list_users	List users with analytics, filterable by activity window and source tenant
update_user_tier	Change subscription tier (free / pro / enterprise)
adjust_user_credits	Add (+) or deduct (–) credits

Featured Minds Portal — full CRUD

The catalog (featured_minds collection) and the linked owner profile (user_profiles) edited together so changes hit https://m-i-n-d.ai/m/{username} immediately.

Action	Description
create_featured_mind	Promote a user's MIND into the featured catalog
list_featured_minds	List every featured mind with mind_id, display_order, featured, is_public
get_featured_mind_full	Bundled view in one round-trip: featured_mind doc + linked user_profile + available_models catalog (what the portal side sheet loads)
update_featured_mind	Catalog fields: title, subtitle, description, tags, featured, display_order, is_public, avatar_url, banner_url, price
update_featured_mind_owner_profile	Write-through to user_profiles for the linked user: preferred_llm_model, public_mind_prompt (≤3000 chars), chat_temperature (0.0–2.0), chat_reasoning_effort (minimal/low/medium/high, thinking models only), public_mind_enabled, public_mind_tagline/greeting/persona, bio, avatar_url, banner_url. Pass null on preferred_llm_model to clear and fall back to platform default.
reorder_featured_minds	Bulk display_order via ordered_mind_ids: string[] — index in list becomes the order. Idempotent.
delete_featured_mind	Remove from catalog. The user's underlying MIND is preserved.

Recipe — change a featured MIND's model + prompt from MCP

mind_admin({ action: "list_featured_minds" })
// → grab the mind_id you want

mind_admin({ action: "get_featured_mind_full", mind_id: "<id>" })
// → see current owner_profile + the full available_models catalog

mind_admin({
  action: "update_featured_mind_owner_profile",
  mind_id: "<id>",
  preferred_llm_model: "anthropic/claude-sonnet-4.6",
  chat_temperature: 0.7,
  public_mind_prompt: "You are Anthony's public MIND. Answer in his voice."
})
// → next anonymous chat at /m/{username} uses the new model + prompt + temp

mind_agents — Agent Command Center (Admin)

Canonical registry of every agent across the workspace fleet — running on a VPS, planned, archived. Solves the recurring "every Claude Code session re-discovers my agents from scratch" problem. Backed by /admin/agents on the MIND backend. Requires an admin API key.

Action	Description
list	List/search agents with filters (list_status, list_host, list_tag, list_query free-text) and a fleet-wide stats payload
get	Detail for one agent + last 20 activities inline
create	Register a new agent record (slug must be unique)
update	Partial update — name, description, status, cadence, host, responsibilities, etc.
delete	Soft-archive (default) or hard=true to permanently remove
heartbeat	Push a heartbeat from the agent's runtime (updates last_heartbeat + current_job)
probe	Active liveness probe (HTTP health_url or OpenClaw gateway) — logs result as activity
log_activity	Append a manual activity entry (notes, status changes, errors)
list_activities	Paginated activity history for one agent
set_status	Shortcut update — flip status to running/paused/planned/archived/error
set_current_job	Shortcut update — record what the agent is doing right now
import_from_mind	Enrich agent records from MIND agent-identity documents
seed_known	Idempotent upsert of the canonical seed list (additive; overwrite=true to reset)
transfer_owner	Move the agent to another MIND account's board (owner_username — the account must exist)
share	Grant another account access — grantee_username + share_role (owner = full control, viewer = read-only)
list_shares	List every account the agent is shared with
revoke_share	Drop a share grant by share_id (from list_shares)

// Before scaffolding a new agent — check what exists
mind_agents({ action: "list" })

// After non-trivial work — keep the registry honest
mind_agents({
  action: "heartbeat",
  slug: "social-media-manager",
  current_job: "drafting LinkedIn carousel for Friday"
})

// Promote a planned agent to running
mind_agents({ action: "set_status", slug: "audit-agent", status: "running" })

// Hand an agent to a teammate's board, or share it read-only
mind_agents({ action: "transfer_owner", slug: "audit-agent", owner_username: "jane" })
mind_agents({ action: "share", slug: "audit-agent", grantee_username: "sam", share_role: "viewer" })

// Search the fleet by free text — slug, name, description, or tags
mind_agents({ action: "list", list_query: "atlas" })

UI: visit https://m-i-n-d.ai/agents (admin-only) to browse the fleet visually.

mind_tickets — Agent Ticket Queue (Admin)

Every agent in the Command Center carries a ticket queue — client feedback, critique, ideas, feature requests, and bugs. A consulting client an agent is shared with files tickets; the agent's owner triages and resolves them. Every ticket auto-assigns to the Ernie triage agent and mirrors into MIND Life as a task. Backed by /admin/agents/{slug}/tickets. Requires an admin API key. agent_slug is required on every call.

Action	Description
list	Every ticket on an agent + open/total stats; optional status filter
get	One ticket plus its full comment thread
create	File a new ticket (title required; kind, body, priority optional)
comment	Answer a ticket — add a reply to its comment thread (body = the reply)
update	Triage — change status, priority, kind, or reassign (assignee)
resolve	Shortcut — mark the ticket resolved
delete	Remove the ticket, its comments, and its mirrored Life task

kind: feedback · critique · idea · feature · bug status: open → triaged → in_progress → resolved → closed priority: low · medium · high · urgent

// File a bug against an agent
mind_tickets({ action: "create", agent_slug: "social-media-manager",
               kind: "bug", priority: "high",
               title: "Carousel export drops the last slide",
               body: "Repro: 7-slide deck exports as 6." })

// Answer it, then resolve it
mind_tickets({ action: "comment", agent_slug: "social-media-manager",
               ticket_id: "<id>", body: "Fixed in the export batch size — verified." })
mind_tickets({ action: "resolve", agent_slug: "social-media-manager", ticket_id: "<id>" })

mind_accounts — Multi-MIND Accounts

A "MIND" is a knowledge-graph account. One person can own — or be granted access to — many MINDs (work, research, a client's, a shared team MIND) and switch between them. This tool lets an agent discover and manage them. Backed by /developer/v1/accounts on the MIND backend.

Action	Description
list	Every MIND your API key's owner can access, with role (owner/viewer) and which is active
create	Spin up a brand-new MIND you own (pass label)
delete	Permanently delete a MIND you own — account, grants, and invitations (pass mind_username)
members	Owners, viewers, and pending invitations of a MIND you own (pass mind_username)
grant	Give an existing MINDapp user owner/viewer access (mind_username, grantee_username, role)
invite	Email an invitation to co-own or view a MIND (mind_username, email, role)

// Discover every MIND you can reach
mind_accounts({ action: "list" })

// Create a dedicated MIND for a new workstream
mind_accounts({ action: "create", label: "Acme Corp Research" })

// Grant a teammate read-only access
mind_accounts({
  action: "grant",
  mind_username: "acme_research_a1b2c3",
  grantee_username: "teammate",
  role: "viewer"
})

Note: owner = full access, viewer = read-only. Requires MULTI_MIND_ACCOUNTS_ENABLED on the MIND backend; list returns enabled: false when the feature is off.

Partner Integration

Partner apps can programmatically create MIND accounts using partner keys:

curl -X POST https://m-i-n-d.ai/admin/users/create \
  -H "X-API-Key: mind_partner_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "username": "newuser",
    "email": "[e-mail]",
    "password": "securepassword",
    "generate_api_key": true
  }'

Returns a JWT + permanent API key. Your app stores the API key and uses it for all subsequent MCP/API calls on behalf of that user.

Environment Variables

Variable	Required	Default	Description
MIND_API_KEY	Yes	—	Your MIND Developer API key
MIND_BASE_URL	No	https://m-i-n-d.ai	MIND API base URL

Programmatic Usage

import { createMindMcpServer, MindClient } from "@astramindapp/mcp-server";

const client = new MindClient({
  baseUrl: "https://m-i-n-d.ai",
  apiKey: "mind_xxx",
});

const server = createMindMcpServer(client);
// Connect to any MCP transport

Patents

MIND's core technology — including emotion-weighted knowledge graph encoding and cross-agent persistent memory via the Model Context Protocol — is the subject of pending patent applications. Patents pending.

Links

• Website: m-i-n-d.ai
• GitHub: theastraway/mind-mcp-server
• npm: @astramindapp/mcp-server
• MCP Docs: m-i-n-d.ai/mcp.html

License

MIT — Astra AI, Inc.