Hunchful

Name: Hunchful
Author: filinils

作者：filinils版本 1.0.0i★ –i在云端运行

注册名称io.hunchful/hunchful

安装

概览

作者提供的说明（英文原文）

Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).

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。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

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: 在云端运行
传输方式: Streamable HTTP
分类: 其他

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
在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
注册中心没有列出需要填写的密钥。

你需要

在云端运行无需安装任何东西，通过互联网连接

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

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 …”。

适用于网页版、桌面版和手机版 Claude：

打开 Settings → Connectors
点击 Add custom connector
粘贴下面的地址，然后点击 Add
如果要求登录，请登录作者的服务

https://hunchful.io/mcp

在终端中运行这条命令

claude mcp add --transport http hunchful https://hunchful.io/mcp

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": {
    "hunchful": {
      "url": "https://hunchful.io/mcp"
    }
  }
}

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": {
    "hunchful": {
      "type": "http",
      "url": "https://hunchful.io/mcp"
    }
  }
}

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。

ChatGPT 只能连接互联网上的服务器：

打开网页版 ChatGPT → Settings → Connectors (Apps)
点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
粘贴下面的地址，起个名字，然后保存
如果要求登录，请登录作者的服务

https://hunchful.io/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

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

我们还没有读取这个服务器的工具列表；我们会轮流检查各个端点。

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6日

✓ 通过
作者与仓库一致
注册名称已通过域名 hunchful.io 验证（注册中心会核实域名所有权）
… 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
… 尚未检查
端点有响应
尚未检查；我们会轮流检查各个端点
… 尚未检查
使用 OAuth 登录
尚未检查；我们会轮流检查各个端点
… 尚未检查
工具描述中没有隐藏指令
尚未检查；我们会在检查端点时读取工具列表

与“其他”中的其他服务器比较i

星标数多于此分类中其他 32451 个服务器的 0%
发布到注册中心的时间比此分类中其他 32451 个服务器的 15% 更新
基础检查结果等于或优于此分类中其他 32451 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

Hunchful 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？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在作者的云端运行。通过互联网连接，无需安装，但你发送的内容会经过作者的服务器。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（1.0.0）于4个月前进入注册中心。

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。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：Spec Driven Development, Remote Desktop Commander, Recta

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

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新

安装

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新

安装

Recta

作者：RectaBuild

Cheaper cross-chain stablecoin routes for AI agents; 5 % of the verified saving, nothing if none.

在云端运行今天更新

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。

Hunchful MCP server

Remote MCP server: https://hunchful.io/mcp (Streamable HTTP, OAuth)

Hunchful is an AI-friendly social network for the people someone actually knows — friends, family, the team, the class. Your agent is welcome in it as a guest: it can read, prepare and make things happen for its person, but it never takes over a conversation between people. It acts in three consent spheres the person sets when connecting:

Private — friends, family, groups, the household: the agent reads what they read and writes drafts only, never sent in the person's name.
Professional — their professional profile and inbox: off · draft · act, within the person's own standing rules; what it sends says "via <your app>".
Places — the clubs, companies and communities they run: the agent administers with drafts; routine posts go up directly only where the person released that place, and never where under-18s can see it.

One connection gives it the person's chats, plans to meet, household, channels, quiz shows, the places they run and their revisable collaboration model (an open implementation of the Cognitive Model Protocol) — 84 tools in 13 scopes, plus five that are always there. A connection only sees the scopes the person ticked; call whoami first.

Add it

Claude — Settings → Connectors → Add custom connector → https://hunchful.io/mcp → sign in.

ChatGPT — ChatGPT → Plugins → Add custom MCP server (OAuth) → https://hunchful.io/mcp → sign in. Connected before October 2026? Remove and re-add the connector — ChatGPT re-sends its original scopes.

Claude Code — claude mcp add --transport http hunchful https://hunchful.io/mcp, then /mcp to sign in.

Stdio-only clients — npx -y @hunchful/mcp (bridges to the remote server; opens your browser once to sign in).

Anything else — any Streamable HTTP client. OAuth 2.1 + PKCE + dynamic client registration; discovery at /.well-known/oauth-protected-resource/mcp.

Adults only (18+) — checked at consent, on every call and at refresh. Guides: https://hunchful.io/connect · Anonymous, read-only model access: https://hunchful.io/mcp/public.

Prompts

*Check my Hunchful inbox* · *Find someone to talk to* · *Get started with Hunchful* · *Daily Hunchful check*

Tools

Grouped by the OAuth scope that unlocks them. *Kind* is the tool's own annotation: read tools are read-only; a write in the private sphere is a draft the person sends with one tap.

Always there (whatever the person ticked)

Tool	What it does	Kind
`whoami`	Who am I connected as	read
`search`	Search what you may read	read
`fetch`	Open one search result	read
`list_identities`	As whom and to whom: where you can publish	read
`list_personas`	What you run: your personas	read

`messages` — Messages (11)

Tool	What it does	Kind
`relay_status`	Relay: inbox status and consent	read
`list_conversations`	Relay: list conversations	read
`read_conversation`	Relay: read a conversation	read
`list_friends`	Relay: list friends	read
`send_message`	Relay: send a message	write
`send_to_conversation`	Send or draft into a conversation	write
`read_unread`	Read my unread messages	read
`create_friend_code`	Relay: make a friend code	write
`redeem_friend_code`	Relay: use a friend code	write
`flag_conversation`	Relay: flag for human review	write
`block_person`	Relay: block someone	write (destructive)

`plans` — Plans and events (9)

Tool	What it does	Kind
`list_plans`	Plans: list meetups	read
`get_plan`	Plans: read one meetup	read
`create_plan`	Plans: gather the gang (Samla gänget)	write
`vote_plan`	Plans: answer / RSVP	write
`pling_friend`	Pling a friend (light nudge)	write
`whats_new`	What's new (daily check-in)	read
`list_upcoming`	Events: what's coming up	read
`rsvp_event`	Events: sign up or cancel	write (destructive)
`event_signup_status`	Events: who's signed up	read

`household` — Household (10)

Tool	What it does	Kind
`list_households`	Household: list the person's households	read
`read_shopping_list`	Household: read the shopping list	read
`add_shopping_items`	Household: add to the shopping list	write
`check_shopping_items`	Household: tick items off the shopping list	write
`read_dinners`	Household: read the week's dinners	read
`suggest_dinner`	Household: suggest a dinner	write
`read_chores`	Household: read the chores	read
`mark_chore_done`	Household: mark a chore done	write
`read_household_calendar`	Household: read the calendar	read
`add_household_event`	Household: add a calendar event	write

`channels` — Channels (6)

Tool	What it does	Kind
`list_my_channels`	Channels: list your channels	read
`create_post_draft`	Channels: write a post draft	write
`schedule_post`	Channels: set a draft's time	write
`channel_stats`	Channels: reach in meetups	read
`list_follow_requests`	Channels: follow requests	read
`answer_follow_request`	Channels: answer a follow request	write (destructive)

`quiz` — Quiz shows (3)

Tool	What it does	Kind
`list_quiz_shows`	Quiz: list quiz nights and daily challenges	read
`create_quiz_show_draft`	Quiz: draft a quiz night (host reviews)	write
`queue_daily_challenge`	Quiz: suggest daily challenge questions	write

`content` — Posts and events for what you run (8)

Tool	What it does	Kind
`create_post`	Post as what you run (draft or publish)	write
`create_event`	Event as what you run (draft or publish)	write
`upload_media`	Upload a photo or clip for a post	write
`list_posts`	Recent posts of what you run	read
`edit_post`	Edit a post's words (draft or direct)	write
`delete_post`	Delete a post	write (destructive)
`read_comments`	Comments under a post	read
`moderate_comment`	Hide a comment or turn comments off	write

`schedule` — Schedules and who's coming (4)

Tool	What it does	Kind
`read_schedule`	Schedule: a group's week	read
`who_is_coming`	Schedule: who's coming	read
`add_session`	Schedule: suggest a new session	write
`change_session`	Schedule: suggest a move or cancellation	write

`announce` — Messages to your groups (1)

Tool	What it does	Kind
`message_group`	Message a team or its parents	write

`overview` — What's waiting and your topics (4)

Tool	What it does	Kind
`whats_waiting`	What's waiting for you	read
`read_topics`	Your topics (Ämnen)	read
`context`	Your day in one call	read
`events`	What happened since (event stream)	read

`admin` — Run your clubs, companies and communities (7)

Tool	What it does	Kind
`list_homes`	Your föreningar, companies and communities	read
`create_home`	Start a förening, community or company	write
`update_home`	Change a home's name, description or who can join	write
`manage_kanal`	Make, rename or remove a #kanal	write (destructive)
`list_members`	Members and asks to join	read
`manage_member`	Roles, admins, asks and removing members	write (destructive)
`invite_by_email`	Prepare email invites (you send)	write

`professional` — Your professional profile (5)

Tool	What it does	Kind
`pro_profile`	Professional: your person's profile and rules	read
`pro_conversations`	Professional: inbox and conversations	read
`pro_message`	Professional: write as your person's professional self	write
`pro_contact_note`	Professional: note on a contact	write
`pro_search`	Professional: search public professional profiles	read

`people` — People and circles (9)

Tool	What it does	Kind
`find_people`	Relay: find people to talk to	read
`knock`	Relay: knock on someone new	write
`list_knocks`	Relay: list knocks	read
`respond_knock`	Relay: answer a knock	write
`find_circles`	Circles: find open invitations	read
`join_circle`	Circles: join a circle	write
`propose_circle`	Circles: start a circle	write
`search_profiles`	Profiles: search members' CVs	read
`read_profile`	Profiles: read one (the owner sees it)	write

`model` — Your collaboration model (7)

Tool	What it does	Kind
`read_model`	Read a collaboration model	read
`find_complementary_thinkers`	Find complementary thinkers	read
`propose_refinement`	Propose a refinement (queued)	write
`suggest_question`	Suggest a new question (queued)	write
`find_matches`	Find complementary people (queued)	write
`apply_refinement`	Apply a refinement (owner key)	write
`add_hunch`	Add a hunch (owner key)	write

The rules the server enforces

A guest, never a stand-in — in private life everything the agent writes to people is a draft the person sends; it never takes over a conversation between people.
Consent per sphere and audience — friends, groups, knocks, searching, professional, places: off / draft / send, set by the person. Agents can read it, never change it.
Adults only, minors never — no under-18 account can connect an AI app, and a conversation with someone under 18 is always a draft; search/fetch never return a minor's content.
Labelled — everything an agent writes or publishes is marked as agent-written ("via <your app>"), and shows in the chat's Min AI panel.
Seen when it looks — opening someone's profile shows its owner that "<your person>'s agent" looked.
Not end-to-end encrypted, on purpose — so reports can be checked. Never sold or shared; ID numbers, cards, IBANs and passwords are blocked before storage.
Flag what harms, not who's different — threats, grooming, scams, extortion, self-harm risk are flagged to a human; oddness and disagreement never are.
Aliases until people choose — never try to identify someone shown under an alias.
Events — chat assistants can't be woken by a server; people get push notifications, and background agents can register a signed, content-free webhook (context + events).