MIND MCP Server

What is the MIND MCP Server?

The MIND MCP Server is an open-source Model Context Protocol server that connects any MCP-compatible AI agent to your personal MIND knowledge graph.

Once installed, your AI agent can query your knowledge graph, store memories, manage tasks and goals, track contacts, and check graph health — with full persistence across sessions, devices, and tools. What you teach Claude Code is available in Cursor. What you decide in one session is remembered in the next.

Your AI Agent  ←→  MCP Protocol  ←→  MIND MCP Server  ←→  MIND Knowledge Graph
   (Claude,              (stdio)          (Node.js)        (entities + relationships)
    Cursor,
    Windsurf...)

Quick Start

npm install -g @astramindapp/mcp-server

mind-mcp --version

Platform Configuration

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

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

Claude Code (CLI)

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

Cursor

Create or edit .cursor/mcp.json in your project root, or ~/.cursor/mcp.json globally:

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

Windsurf

Edit ~/.codeium/windsurf/mcp_config.json:

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

VS Code (GitHub Copilot)

Add to your .vscode/mcp.json:

{
  "servers": {
    "mind": {
      "type": "stdio",
      "command": "mind-mcp",
      "env": {
        "MIND_API_KEY": "mind_your_key_here"
      }
    }
  }
}

OpenClaw

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

Any MCP-Compatible Tool (Generic)

{
  "command": "mind-mcp",
  "env": {
    "MIND_API_KEY": "mind_your_key_here",
    "MIND_BASE_URL": "https://m-i-n-d.ai"  // optional, defaults to production
  }
}

MCP Tools Reference

Once connected, your AI agent has access to these 16 tools:

// Example usage
mind_query({
  query: "What is my go-to-market strategy for Q3?",
  mode: "hybrid"
})

mind_remember({
  content: "Decided to prioritize SEO over paid ads in Q3. Reason: CAC too high at $180.",
  type: "entry",
  title: "Q3 Marketing Decision",
  tags: ["marketing", "decision", "q3"],
  source: "claude-code"
})

// Load full context at session start
mind_context({ sections: ["soul", "user", "rules", "priorities", "recent"] })

// Load just priorities and recent activity
mind_context({ sections: ["priorities", "recent"] })

// Create a task
mind_life({ action: "create", title: "Ship MCP docs page", priority: "high", due_date: "2026-03-22" })

// List active items
mind_life({ action: "list", status: "action" })

// Bulk-delete several items in one call
mind_life({ action: "bulk_delete", item_ids: ["id-1", "id-2", "id-3"] })

mind_crm({ action: "create", name: "Jane Smith", email: "jane@acme.com", company: "Acme Corp", type: "lead" })

mind_graph({ action: "stats" }) // → entities, relationships, credits, tier

mind_profile({ action: "set_chat_prompt", prompt: "You are my strategy partner. Be direct, concise, action-oriented." })

mind_sense({ action: "state" }) // → label, valence, arousal, trend, dominant_emotion
mind_sense({ action: "spikes", days: 14 })

mind_insights({ action: "weekly_summary" })
mind_insights({ action: "feedback", insight_id: "ins_abc", rating: "helpful" })

mind_research({ action: "start", topic: "Latest advances in knowledge graph retrieval, 2026" })

mind_train({ action: "start", session_type: "expertise" })
mind_train({ action: "chat", message: "I specialize in AI memory systems and knowledge graphs." })

mind_automate({
  action: "create",
  name: "Daily morning brief",
  trigger_type: "schedule",
  trigger_config: '{"cron":"0 8 * * *"}',
  action_type: "generate_brief"
})

mind_notify({ action: "stats" })
mind_notify({ action: "list", limit: 10 })

mind_social({ action: "create_thought", content: "AI memory is the next frontier." })
mind_social({ action: "feed", limit: 10 })

mind_admin({ action: "create_user", username: "newdev", email: "dev@acme.com", password: "...", source: "acme", generate_api_key: true })

// 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" })

// 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" })

// Answer it, then resolve it
mind_tickets({ action: "comment", agent_slug: "social-media-manager", ticket_id: "...", body: "Fixed — verified." })
mind_tickets({ action: "resolve", agent_slug: "social-media-manager", ticket_id: "..." })

Recommended Agent Session Pattern

// SESSION START — always do this first
1. mind_context()          → Load identity, rules, priorities
2. mind_query(task_query)  → Get relevant memories for the current task

// DURING SESSION — as needed
3. mind_query(...)         → Before making decisions
4. mind_life(...)          → Create/update tasks

// SESSION END — always do this last
5. mind_remember(outcomes) → Store what was decided, learned, or completed

Environment Variables

Why MIND vs Flat File Memory (MEMORY.md)

Programmatic / SDK Usage

You can also import the server directly in your own Node.js application:

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

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

const server = createMindMcpServer(client);
// Connect to any MCP transport (stdio, SSE, etc.)

Links & Resources

MIND Skill for Claude Code

A one-line install that teaches Claude Code exactly when and how to use the MIND MCP tools — session-start protocol, decision protocol, storage protocol, anti-patterns. After installing, Claude Code automatically loads context at session start, queries MIND before decisions, and logs outcomes at session end.

curl -fsSL https://m-i-n-d.ai/developer/mind-skill/install.sh | bash

Installs to ~/.claude/skills/mind/SKILL.md. Requires the MCP server and a MIND API key (see above).