MCP Marketplace
BrowseHow It WorksFor CreatorsDocs
Sign inSign up
MCP Marketplace

The curated, security-first marketplace for AI tools.

Product

Browse ToolsSubmit a ToolDocumentationHow It WorksBlogFAQChangelog

Legal

Terms of ServicePrivacy PolicyCommunity Guidelines

Connect

support@mcp-marketplace.ioTwitter / XDiscord

MCP Marketplace © 2026. All rights reserved.

Back to Browse

Mind MCP Server

by Theastraway
Developer ToolsModerate5.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Personal knowledge graph AI memory. 15 tools, 89 actions. Emotional intelligence, CRM, social.

About

Personal knowledge graph AI memory. 15 tools, 89 actions. Emotional intelligence, CRM, social.

Security Report

5.0
Moderate5.0Moderate Risk

Valid MCP server (2 strong, 3 medium validity signals). 4 known CVEs in dependencies (1 critical, 3 high severity) Package registry verified. Imported from the Official MCP Registry.

3 files analyzed · 5 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

What You'll Need

Set these up before or after installing:

Your MIND Developer API key (get one at m-i-n-d.ai)Required

Environment variable: MIND_API_KEY

MIND API base URLOptional

Environment variable: MIND_BASE_URL

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "io-github-theastraway-mind": {
      "env": {
        "MIND_API_KEY": "your-mind-api-key-here",
        "MIND_BASE_URL": "your-mind-base-url-here"
      },
      "args": [
        "-y",
        "@astramindapp/mcp-server"
      ],
      "command": "npx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

@astramindapp/mcp-server

MIND MCP Server — The most complete AI memory layer available. 15 tools, 89 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.

15 Tools

ToolActionsWhat It Does
mind_query1Semantic search across your knowledge graph (5 search modes)
mind_remember5Store, search, get, list, delete — documents, entries, thoughts
mind_context1Load persistent identity, preferences, rules, priorities, recent activity
mind_life12Goals, projects, tasks + full calendar management + productivity stats
mind_crm7Contacts, pipeline, activity logging, interaction history
mind_graph3Graph stats, diagnostics, entity labels
mind_admin7User provisioning, featured minds, tier/credit management
mind_sense7MINDsense emotional intelligence — state, signals, timeline, KG weights, spikes
mind_research3Launch autonomous deep research jobs
mind_train7Self-training sessions + save chats to knowledge graph
mind_social14Thoughts (posts), social feed, communities, likes, comments
mind_profile9Profile, custom system prompts, LLM model selection
mind_insights7Autonomous Learning Engine insights, weekly summaries, feedback
mind_automate6Scheduled automations, event triggers, execution history
mind_notify4Notifications, mark read, stats

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
  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 FilesMIND
Size~20K chars, truncatedUnlimited knowledge graph
RetrievalLoads everything every turnOnly relevant memories via semantic search
StructureUnstructured textGraph with entities, relationships, and emotional weights
Cross-agentOne tool onlyShared across all AI agents
IntelligenceNoneAutonomous pattern detection + emotional encoding

vs. Other MCP Memory Servers

Anthropic OfficialMem0Graphiti/ZepMIND
Tools84915
Knowledge graphBasic (JSON)No (vectors)Yes (Neo4j)Yes (LightRAG)
Emotional intelligenceNoNoNoYes (patented)
CRMNoNoNoYes
Life managementNoNoNoYes
Social featuresNoNoNoYes
Self-trainingNoNoNoYes
Research agentNoNoNoYes
AutomationsNoNoNoYes
Mobile appNoNoNoYes

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

ActionDescription
createStore content (auto-categorized as document, entry, or thought)
deleteRemove by ID
searchFind entries/thoughts by query
getRetrieve specific item by ID
listPaginated 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

ActionDescription
list, create, update, complete, delete, move, getFull task/goal CRUD
calendar_list, calendar_create, calendar_update, calendar_deleteCalendar events
statsProductivity metrics and completion rates

mind_crm — Contact Relationship Management

ActionDescription
list, create, update, delete, getContact CRUD with pipeline stages
log_activityRecord calls, emails, meetings, notes
list_activitiesView interaction history

mind_sense — MINDsense Emotional Intelligence

ActionDescription
stateCurrent emotional state (valence, arousal, trend, sensitivity)
signalsRecent emotional signals with strength and source
timelineHistorical emotional data
kg_weightsEntities weighted by emotional significance
spikesDetected emotional spikes
acknowledgeMark a spike as acknowledged
summaryAI-generated emotional summary

mind_research — Autonomous Research

ActionDescription
startLaunch a deep research job on any topic
statusCheck job progress
listView all research jobs

mind_train — Self-Training

ActionDescription
startBegin guided training (basics, network, expertise, history, goals, freeform)
chatSend training message
status, list_sessions, pause, resumeSession management
save_chatSave any chat conversation into the knowledge graph

mind_social — Social Layer

ActionDescription
create_thought, get_thought, delete_thought, like_thoughtThought (post) management
feed, user_feed, search_feedSocial feed browsing
create_community, list_communities, get_communityCommunity management
join_community, leave_communityMembership
create_post, list_postsCommunity posts

mind_profile — Profile & Preferences

ActionDescription
get, updateProfile management
get_chat_prompt, set_chat_promptCustom chat system prompt
get_thought_prompt, set_thought_promptCustom thought generation prompt
get_model, set_model, list_modelsLLM model selection (50+ models)

mind_insights — Autonomous Learning Engine

ActionDescription
listRecent pattern-detected insights
unread_countCount of unseen insights
view, feedbackMark seen, rate helpfulness
analyzeTrigger on-demand analysis
weekly_summaryWeekly intelligence summary
contextALE context data

mind_automate — Automations

ActionDescription
list, create, update, deleteAutomation CRUD
run_nowTrigger immediately
historyExecution log

mind_notify — Notifications

ActionDescription
listView all notifications
mark_read, mark_all_readRead management
statsNotification overview

mind_admin — Administration

ActionDescription
create_userProvision new MIND account
list_usersList users with analytics
update_user_tierChange subscription tier
adjust_user_creditsAdd/deduct credits
create_featured_mindCreate public featured mind
list_featured_minds, update_featured_mindFeatured minds catalog

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": "user@app.com",
    "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

VariableRequiredDefaultDescription
MIND_API_KEYYes—Your MIND Developer API key
MIND_BASE_URLNohttps://m-i-n-d.aiMIND 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 technology is protected by multiple provisional patents including:

  • Emotion-Weighted Knowledge Graph Encoding (U.S. App. 64/030,662)
  • Cross-Agent Persistent Memory via Model Context Protocol

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.

Reviews

No reviews yet

Be the first to review this server!

0

installs

New

no ratings yet

Is this your server?

Claim ownership to manage your listing, respond to reviews, and track installs from your dashboard.

Claim with GitHub

Sign up with the GitHub account that owns this repo

Links

Source Codenpm Package

Details

Published April 8, 2026
Version 0.5.4
1 stars
0 installs
Local Plugin

More Developer Tools MCP Servers

Git

Free

by Modelcontextprotocol · Developer Tools

Read, search, and manipulate Git repositories programmatically

80.0K
Stars
4
Installs
6.5
Security
No ratings yet
Local

Toleno

Free

by Toleno · Developer Tools

Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.

114
Stars
409
Installs
8.0
Security
4.8
Local

mcp-creator-python

Free

by mcp-marketplace · Developer Tools

Create, build, and publish Python MCP servers to PyPI — conversationally.

-
Stars
56
Installs
10.0
Security
5.0
Local

MarkItDown

Free

by Microsoft · Content & Media

Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption

116.1K
Stars
15
Installs
6.0
Security
5.0
Local

mcp-creator-typescript

Free

by mcp-marketplace · Developer Tools

Scaffold, build, and publish TypeScript MCP servers to npm — conversationally

-
Stars
14
Installs
10.0
Security
5.0
Local

FinAgent

Free

by mcp-marketplace · Finance

Free stock data and market news for any MCP-compatible AI assistant.

-
Stars
13
Installs
10.0
Security
No ratings yet
Local