Show HN: MindThread CLI and MCP server for Threads, with per-permission approval

Let Claude, Cursor or any MCP client write, schedule and publish Threads posts, review drafted replies and read insights for your accounts, through Meta's official Threads API. 40+ tools, a free sandbox key, and permission controls so the agent asks before it posts.

claude mcp add --transport http mindthread https://mindthread.tw/api/mcp --header "Authorization: Bearer mt_live_your_key"

• Write : generate 1 to 5 drafts in the account's voice (persona, brand material, content formulas), or threads of 2 to 10 parts.
• Schedule and publish : text, single image, carousel (2 to 10 images) or video, now or at an exact time; or drop posts into a queue that publishes at the account's own time slots.
• Stay on-brand in code : content rules (length, banned phrases, no hashtags, only numbers from your fact list) are enforced by the server, not just suggested in a prompt.
• Reply where it matters : cloud patrol searches Threads for your keywords and drafts replies; your agent lists the drafts and approves or rejects each one.
• Measure : views, likes, replies and followers per account, plus the results of patrol replies.
• Stay in control : every key has per-permissionallow ,ask ordeny . Withask , the post waits until you confirm it on mindthread.tw, and the agent gets a link to hand you instead of posting.

1. Get an API key. Sign up at mindthread.tw, connect a Threads account, then open Settings → API keys and create a key. Start with a test key (mt_test_…): reads show your real data, writes are simulated and nothing reaches Threads. Switch to a live key (mt_live_…) when you are ready. Every plan includes API access (October 2026: free plan 50 calls a day per live key; test keys share a 500-a-day sandbox). Current limits: mindthread.tw/developers.

2. Add MindThread to your client (pick yours below).

3. Ask for your first scheduled post:

List my MindThread accounts. Then write a short post about why I started my business, show it to me, and schedule it on my account for tomorrow at 9:00 Taipei time.

The agent calls list_accounts, generate_posts, then publish with publish_at. Check the result with "show my scheduled posts" ( list_schedules).

There are two ways to connect, and both reach the same server:

• Remote (recommended) : point the client athttps://mindthread.tw/api/mcp . Nothing to install.
• Local stdio : run this package withnpx -y mindthread-mcp . Use it for clients that only start servers with a command. It forwards every message to the same endpoint, so the tools are always identical.

claude mcp add --transport http mindthread https://mindthread.tw/api/mcp --header "Authorization: Bearer mt_live_your_key"

claude mcp add --transport http mindthread https://mindthread.tw/api/mcp

claude mcp add mindthread --env MINDTHREAD_API_KEY=mt_live_your_key -- npx -y mindthread-mcp

Edit claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "mindthread": {
      "command": "npx",
      "args": ["-y", "mindthread-mcp"],
      "env": { "MINDTHREAD_API_KEY": "mt_live_your_key" }
    }
  }
}

On Windows, if Claude cannot find npx, use "command": "cmd" and "args": ["/c", "npx", "-y", "mindthread-mcp"]. Without editing files: Settings → Connectors → Add custom connector, URL https://mindthread.tw/api/mcp, then sign in with your MindThread account (on Claude plans that offer custom connectors).

~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):

{
  "mcpServers": {
    "mindthread": {
      "url": "https://mindthread.tw/api/mcp",
      "headers": { "Authorization": "Bearer mt_live_your_key" }
    }
  }
}

Or the stdio form: "command": "npx", "args": ["-y", "mindthread-mcp"], "env": { "MINDTHREAD_API_KEY": "mt_live_your_key" }.

.vscode/mcp.json, which asks for the key once and stores it securely:

{
  "inputs": [
    { "type": "promptString", "id": "mindthread-key", "description": "MindThread API key", "password": true }
  ],
  "servers": {
    "mindthread": {
      "type": "http",
      "url": "https://mindthread.tw/api/mcp",
      "headers": { "Authorization": "Bearer ${input:mindthread-key}" }
    }
  }
}

• Streamable HTTP: https://mindthread.tw/api/mcp , headerAuthorization: Bearer <key> (also accepted asX-API-Key ).
• stdio: command npx , args-y mindthread-mcp , envMINDTHREAD_API_KEY .

Without a key, initialize, tools/list, get_playbook and list_formulas still work, so you can look around first.

• "What can MindThread do? Read the playbook first." (get_playbook )
• "Write 3 posts about saving for a first home in @mybrand's voice. Don't post anything yet." (generate_posts )
• "Queue posts 1 and 3; schedule post 2 for Friday 20:00." (add_library ,publish )
• "Any drafted replies waiting for me? Show them one by one." (list_pending_replies ,approve_pending_reply ,reject_pending_reply )
• "How did @mybrand do in the last 7 days compared with the 7 days before?" (analytics_insights )
• "Set cloud patrol keywords to 'first home', 'mortgage', 'rent vs buy', at most 10 replies a day, and hold every reply for my review." (set_cloud_patrol )

The set any client sees before signing in, generated from the live server with npm run tools-table. The server is the source of truth: when it adds a tool, this package exposes it without an update.

• Permissions per key. Each permission (read, write drafts, schedule, publish now, send replies, turn cloud patrol on, connect accounts, loosen guardrails, webhooks) isallow ,ask ordeny , set in Settings → API keys.ask means the agent receivesapproval_required with a link for you; the action runs only after you confirm on mindthread.tw.
• Things only you do on the website. Undoing a guardrail change is always yours. Turning cloud patrol on is never granted to an OAuth connection (Claude, ChatGPT), and an API key needs that permission set explicitly.
• Content rules run in code.enforce: "block" makes the server refuse a post that breaks the rules, whatever the model wrote.
• Kill switch.disable_this_key permanently disables the key in use. You can also revoke keys and connections in Settings.
• Official API only. Posting and replies go through Meta's official Threads API. MindThread never asks for your Threads password.
• Your key stays local. In stdio mode the key is read from theMINDTHREAD_API_KEY environment variable and sent only tomindthread.tw . It is never printed (logs showmt_live_…abcd ).

Requires Node.js 18.17 or newer. No runtime dependencies.

• "MINDTHREAD_API_KEY is not set" : add the key to theenv block of this server in your client config, then restart the client.

• "MindThread rejected the key" : the key is wrong, revoked or disabled. Create a new one in Settings → API keys.

• approval_required : working as intended. Open the link the agent shows you, confirm, and the post goes out.

• insufficient_scope : that permission is set to deny for this key. The error'sfix field names the setting to change.

• rate_limit_exceeded : daily or per-minute limit reached; the error says when it resets.

• Logs go to stderr (Claude Desktop: Settings → Developer → Open Logs Folder). stdout carries only MCP messages.

• CLI for scripts and agents that prefer shell commands:mindthread-cli (npx mindthread-cli ).

• REST API : OpenAPI 3.1 atmindthread.tw/api/v1/openapi.json , docs atmindthread.tw/developers , agent guide atmindthread.tw/llms.txt .

MindThread 是給 AI agent 用的 Threads 排程器。接上之後，Claude、Cursor 或任何支援 MCP 的工具，都能替你的 Threads 帳號寫文、排程、發文（文字、單圖、輪播、影片）、審核雲端海巡的回覆草稿、看觀看與互動數據。全程走 Meta 官方 Threads API，不需要你的 Threads 密碼。

三分鐘上手：

1. 到 mindthread.tw 註冊並連接 Threads 帳號，在「設定 → API 金鑰」建立金鑰。建議先用測試金鑰（mt_test_ 開頭）：讀取的是真資料，寫入只模擬、不會發到 Threads。
2. 把 MindThread 加進你的工具，例如 Claude Code： Claude Desktop、Cursor、VS Code 的設定見上方

claude mcp add --transport http mindthread https://mindthread.tw/api/mcp --header "Authorization: Bearer mt_live_你的金鑰"

Client setup 。 3. 對 AI 說：「列出我的 MindThread 帳號，幫我寫一篇介紹我為什麼創業的短文，給我看過之後，排在明天早上 9 點發。」

你保有控制權：每把金鑰的每項權限都能設成「允許」「先問我」「拒絕」。設成「先問我」時，AI 會拿到一個確認連結交給你，你在 mindthread.tw 按下確認才會發出。字數、禁用詞、只能用你列的數字這些內容規則，由伺服器以程式檢查，可以設成直接擋下。

MIT © Ultra Lab