原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

MIND

作者:theastraway版本 0.29.2i★ –i在你的电脑上运行
注册名称io.github.theastraway/mind

安装

概览

作者提供的说明(英文原文)

MIND knowledge-graph memory for agents. 44 tools: CRM, Life, MoneyMIND, Budget, Sheets, Email, Sign.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 搜索与 AI 记忆
  • 你需要填写:MIND_API_KEY

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: MIND_API_KEY, MIND_BASE_URL

标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。

你需要

  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "mind": {
      "command": "npx",
      "args": [
        "-y",
        "@astramindapp/mcp-server"
      ],
      "env": {
        "MIND_API_KEY": "your-value",
        "MIND_BASE_URL": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add mind --env MIND_API_KEY=your-value --env MIND_BASE_URL=your-value -- npx -y @astramindapp/mcp-server

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "mind": {
      "command": "npx",
      "args": [
        "-y",
        "@astramindapp/mcp-server"
      ],
      "env": {
        "MIND_API_KEY": "your-value",
        "MIND_BASE_URL": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "mind": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@astramindapp/mcp-server"
      ],
      "env": {
        "MIND_API_KEY": "your-value",
        "MIND_BASE_URL": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • MIND_API_KEY 机密 必填 env
    Your MIND Developer API key (get one at m-i-n-d.ai)
  • MIND_BASE_URL env
    MIND API base URL

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 theastraway 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 7264 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 7264 个服务器的 47% 更新
  • 基础检查结果等于或优于此分类中其他 7264 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

MIND 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

你需要填写:MIND_API_KEY

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.29.2)于上个月进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它?

同一分类中有:Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者:upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT昨天更新
安装

Codebase Memory

作者:DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT21天前更新
安装

Exa

作者:exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT上个月更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

@astramindapp/mcp-server

MIND MCP Server — The most complete AI memory layer available. 44 tools, 384 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.

44 Tools

ToolActionsWhat It Does
mind_query1Semantic search across your knowledge graph (5 search modes)
mind_remember5Store, search, get, list, delete — document & entry (PRIVATE), feed_post (PUBLIC, explicit user request only — thought kept as deprecated alias)
mind_folders7Organize documents into folders — list, create, rename, move, delete, file documents
mind_folder_routes4Configure deterministic system-folder routing — which folder each kind of system-generated doc (life items, CRM, chat saves, tasks, training, trader signals, cloud imports) is filed into automatically
mind_folder_suggest1Ask MIND which folder a piece of content belongs in, via its routing_hint + a cheap LLM picker
mind_share4Create and manage share links for one MIND document — create (default), list, list_all, revoke
mind_context1Load persistent identity, preferences, rules, priorities, recent activity
mind_life16Goals, projects, tasks + full calendar management + productivity stats
mind_focuses5Focus → Project buckets — the top-level groupings above Life Projects
mind_crm7Contacts, pipeline, activity logging, interaction history
mind_tasks9Site-wide tasks — assignable, completable work items on projects, contacts, or agents, plus completion reports
mind_graph3Graph stats, diagnostics, entity labels
mind_admin11Admin-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_sense7MINDsense emotional intelligence — state, signals, timeline, KG weights, spikes
mind_osint7Operate Ozzie — the autonomous OSINT analyst — for cited intelligence dossiers on a domain/IP/org/person, plus live-feed alerts and watchlists
mind_research3Launch autonomous deep research jobs
mind_train7Self-training sessions + save chats to knowledge graph
mind_social14Public feed posts, social feed, communities, likes, comments — ⚠️ posting writes to the user's PUBLIC feed, only call on explicit user request
mind_social_analytics6YouTube/LinkedIn/X/Twitch channel stats, recent video performance, retention/traffic/sentiment, goal progress
mind_profile9Profile, custom system prompts, LLM model selection
mind_trader25TraderMIND — the agentic trading engine: live feed, MIND Vision forecasts (latest cone + resolved history + per-bar scores), candles, cycles, calibration honesty curve, engine health, save/star/like + undo, notes + structured feedback the engine learns from, full trading-journal CRUD, personalized insights. Engine reads + counts are public (work even with no/invalid key); only the act-as-you actions authenticate as the key's owner
mind_insights7Autonomous Learning Engine insights, weekly summaries, feedback
mind_automate6Scheduled automations, event triggers, execution history
mind_notify4Notifications, mark read, stats
mind_agents25Admin-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_tickets7Admin-only. Agent ticket queue — file, view, answer (comment), triage, resolve, and delete client feedback / bugs / ideas on any agent
mind_personas17Admin-only. Influencer Factory Command Center — synthetic-persona CRUD, face anchor + variants, ElevenLabs voice, per-platform bios, Blotato account registration
mind_accounts6Multi-MIND accounts — list MINDs you can access, create new ones, delete MINDs you own, manage owners/viewers, send email invitations
mind_list_templates1List the 16 Front Layer typed-document templates
mind_get_template1Fetch the full spec for one Front Layer template
mind_save_typed1Save a filled-out Front Layer document with its type tag
mind_bootstrap_templates1Seed all 16 Front Layer templates into a MIND tenant
mind_mindmap6MIND Mind Map (m-i-n-d.ai/#/mind-map) — visual canvases: list/get/create/update/delete, read a public shared map. Sharing, collaborators and AI generation from a prompt/project stay in the web app (JWT-only, human-only)
mind_moneymind37MoneyMIND (m-i-n-d.ai/#/moneyMIND) — accounts, transactions + splits + rules, budgets, recurring bills, net worth, savings goals, credit, alerts, bill negotiation, bank statements
mind_budget1913-week cash-flow planner (m-i-n-d.ai/#/budget) — cells, rows, quarters, variance, roll-forward, autofill/build from bank statements
mind_sheets14Airtable-style tables (m-i-n-d.ai/#/sheets) — tables, columns, rows, CSV export
mind_email14MIND Email Manager (m-i-n-d.ai/#/email) — inbox, threads, search, AI draft, ⚠️ send (outward), voice/tone preferences
mind_checklists13Kanon checklists (kanon.theastraway.com) attached to Life items or tasks — templates, runs, toggle_item, progress rollups
mind_sign12MIND Sign e-signature (m-i-n-d.ai/#/mindsign) — envelopes, fields, ⚠️ send/resend (outward), void, audit, certificate
mind_invoices9Invoice Agent (m-i-n-d.ai/#/invoiceagent) — create/update, ask a question about an invoice, ⚠️ invite (outward), received invoices
mind_books9MIND Books accounting (m-i-n-d.ai/#/mind-books) — vendors, customers, chart of accounts, bills, invoices overview
mind_timer8Tempo time tracking — start/stop, manual entries, summaries
mind_forms7Quill lead-capture forms (m-i-n-d.ai/#/forms) — build, read submissions, public read by slug
mind_library8Personal bookshelf (m-i-n-d.ai/#/library) — authors, books, chapter content, AI reading companion

Quick Start

Fastest: one-paste remote connect (Claude Code / Claude Desktop / claude.ai)

No install, no API key handling — paste one command, click Connect in the browser, done:

claude mcp add --transport http mind https://www.m-i-n-d.ai/mcp

Claude opens the m-i-n-d.ai consent page, you click Connect, and MIND is live. Auth, key minting, and refresh are all handled by OAuth.

No browser OAuth in your host? Use a key on the same URL

Every host that lets you add a custom MCP server with a header can use MIND with no OAuth and no npm install: same remote server URL, just swap in a key.

  • Server URL: https://www.m-i-n-d.ai/mcp
  • Header: Authorization: Bearer mind_
  • Mint a key: https://www.m-i-n-d.ai → Settings → Developer → API Keys

Agents: if AuthenticateMcpServer or the host's connect card fails, ask the user for a MIND API key and rewire the same URL with that header — do not fall back to the local npm server just because OAuth didn't work.

Local stdio install: browser-connect setup wizard

For tools that run MCP servers locally (Claude Desktop, Cursor, Windsurf, VS Code Copilot), run the setup wizard — it opens your browser, you click Connect on m-i-n-d.ai, and it receives your API key automatically and writes every tool config for you:

npx -y --package=@astramindapp/mcp-server mind-mcp-setup

No manual key copying. The wizard auto-detects your installed AI tools and configures each one.

Manual alternative: paste an API key

If you'd rather mint a key yourself: sign up at www.m-i-n-d.ai → Settings → Developer → Create API Key, then:

npx -y --package=@astramindapp/mcp-server mind-mcp-setup --key mind_xxx

or install globally and configure by hand:

npm install -g @astramindapp/mcp-server
Claude Code (local stdio with a manual key)
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" } } } }

The config file lives at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS, or %APPDATA%\Claude\claude_desktop_config.json on Windows. Fully quit and reopen Claude Desktop after editing — it only reads this file on launch.

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
Tools84924
Knowledge graphBasic (JSON)No (vectors)Yes (Neo4j)Yes (per-user MIND graph)
Emotional intelligenceNoNoNoYes (patent-pending)
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 authenticat

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx