mind-mcp-server

# @astramindapp/mcp-server

**MIND MCP Server** — The most complete AI memory layer available. 31 tools, 208 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, social features, self-training, autonomous insights, and more.

## 31 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_context` | 1 | Load persistent identity, preferences, rules, priorities, recent activity |
| `mind_focuses` | 5 | Top-level Focus buckets that group Life projects |
| `mind_life` | 16 | Focus → Project → Outcome hierarchy + calendar + cross-account sharing + stats |
| `mind_tasks` | 9 | Assignable, completable, reportable work items on Life/CRM/agents or standalone |
| `mind_checklists` | 9 | Task-level checklists — templates, phase-bucketed steps, completion tracking |
| `mind_crm` | 7 | Contacts, pipeline, activity logging, interaction history |
| `mind_graph` | 3 | Graph stats, diagnostics, entity labels |
| `mind_admin` | 11 | User provisioning, Featured Minds Portal, tier/credit management (admin-only) |
| `mind_sense` | 7 | MINDsense emotional intelligence — state, signals, timeline, KG weights, spikes |
| `mind_research` | 3 | Launch and track 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_folders` | 7 | Organize documents into folders (a presentation layer over the graph) |
| `mind_folder_routes` | 4 | Deterministic system-folder routing for auto-filed docs |
| `mind_folder_suggest` | 1 | Ask MIND which folder a piece of content belongs in |
| `mind_list_templates` | 1 | List the 16 MIND Front Layer template types |
| `mind_get_template` | 1 | Fetch the full markdown spec for one Front Layer template |
| `mind_save_typed` | 1 | Save a filled Front Layer document with its type tag |
| `mind_bootstrap_templates` | 1 | Seed all 16 Front Layer templates into a tenant |
| `mind_agents` | 25 | Admin-only Agent Command Center — registry, status, invoices, workflows |
| `mind_tickets` | 7 | Agent ticket queue — file, triage, resolve client feedback/bugs |
| `mind_accounts` | 6 | Manage multi-MIND accounts — list, create, delete, members, grant, invite |
| `mind_social_analytics` | 6 | YouTube/LinkedIn/X/Twitch channel analytics from the Social Dashboard |
| `mind_personas` | 17 | Influencer Factory Command Center — synthetic personas across Blotato platforms (admin-only) |
| `mind_osint` | 7 | Operate Ozzie, the autonomous OSINT analyst — investigate targets, monitors, watchlists |

## Quick Start

### 1. Get a MIND API Key

Sign up at [m-i-n-d.ai](https://m-i-n-d.ai) → Settings → Developer → Create API Key

### 2. Install

```bash
npm install -g @astramindapp/mcp-server
```

### 3. Configure Your AI Tool

#### Claude Code

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

#### Claude Desktop

Add to your `claude_desktop_config.json`:

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

#### Cursor

Add to `.cursor/mcp.json`:

```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
```

1. Agent calls `mind_context` at session start → loads identity, rules, priorities
2. Agent calls `mind_query` before decisions → retrieves relevant memories
3. Agent calls `mind_remember` after tasks → stores outcomes and learnings
4. Agent calls `mind_sense` → reads user's emotional state to adapt responses
5. Agent calls `mind_insights` → surfaces autonomous pattern detection
6. 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 | **15** |
| Knowledge graph | Basic (JSON) | No (vectors) | Yes (Neo4j) | **Yes (LightRAG)** |
| Emotional intelligence | No | No | No | **Yes (patented)** |
| 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_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 |
| `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_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 |
|--------|-----------