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.
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.
Related MCP server: @cowork/mcp-server
Check my Hunchful inbox · Find someone to talk to · Get started with Hunchful · Daily Hunchful check
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 |
| Who am I connected as | read |
| Search what you may read | read |
| Open one search result | read |
| As whom and to whom: where you can publish | read |
| What you run: your personas | read |
messages — Messages (11)
Tool | What it does | Kind |
| Relay: inbox status and consent | read |
| Relay: list conversations | read |
| Relay: read a conversation | read |
| Relay: list friends | read |
| Relay: send a message | write |
| Send or draft into a conversation | write |
| Read my unread messages | read |
| Relay: make a friend code | write |
| Relay: use a friend code | write |
| Relay: flag for human review | write |
| Relay: block someone | write (destructive) |
plans — Plans and events (9)
Tool | What it does | Kind |
| Plans: list meetups | read |
| Plans: read one meetup | read |
| Plans: gather the gang (Samla gänget) | write |
| Plans: answer / RSVP | write |
| Pling a friend (light nudge) | write |
| What's new (daily check-in) | read |
| Events: what's coming up | read |
| Events: sign up or cancel | write (destructive) |
| Events: who's signed up | read |
household — Household (10)
Tool | What it does | Kind |
| Household: list the person's households | read |
| Household: read the shopping list | read |
| Household: add to the shopping list | write |
| Household: tick items off the shopping list | write |
| Household: read the week's dinners | read |
| Household: suggest a dinner | write |
| Household: read the chores | read |
| Household: mark a chore done | write |
| Household: read the calendar | read |
| Household: add a calendar event | write |
channels — Channels (6)
Tool | What it does | Kind |
| Channels: list your channels | read |
| Channels: write a post draft | write |
| Channels: set a draft's time | write |
| Channels: reach in meetups | read |
| Channels: follow requests | read |
| Channels: answer a follow request | write (destructive) |
quiz — Quiz shows (3)
Tool | What it does | Kind |
| Quiz: list quiz nights and daily challenges | read |
| Quiz: draft a quiz night (host reviews) | write |
| Quiz: suggest daily challenge questions | write |
content — Posts and events for what you run (8)
Tool | What it does | Kind |
| Post as what you run (draft or publish) | write |
| Event as what you run (draft or publish) | write |
| Upload a photo or clip for a post | write |
| Recent posts of what you run | read |
| Edit a post's words (draft or direct) | write |
| Delete a post | write (destructive) |
| Comments under a post | read |
| Hide a comment or turn comments off | write |
schedule — Schedules and who's coming (4)
Tool | What it does | Kind |
| Schedule: a group's week | read |
| Schedule: who's coming | read |
| Schedule: suggest a new session | write |
| Schedule: suggest a move or cancellation | write |
announce — Messages to your groups (1)
Tool | What it does | Kind |
| Message a team or its parents | write |
overview — What's waiting and your topics (4)
Tool | What it does | Kind |
| What's waiting for you | read |
| Your topics (Ämnen) | read |
| Your day in one call | read |
| What happened since (event stream) | read |
admin — Run your clubs, companies and communities (7)
Tool | What it does | Kind |
| Your föreningar, companies and communities | read |
| Start a förening, community or company | write |
| Change a home's name, description or who can join | write |
| Make, rename or remove a #kanal | write (destructive) |
| Members and asks to join | read |
| Roles, admins, asks and removing members | write (destructive) |
| Prepare email invites (you send) | write |
professional — Your professional profile (5)
Tool | What it does | Kind |
| Professional: your person's profile and rules | read |
| Professional: inbox and conversations | read |
| Professional: write as your person's professional self | write |
| Professional: note on a contact | write |
| Professional: search public professional profiles | read |
people — People and circles (9)
Tool | What it does | Kind |
| Relay: find people to talk to | read |
| Relay: knock on someone new | write |
| Relay: list knocks | read |
| Relay: answer a knock | write |
| Circles: find open invitations | read |
| Circles: join a circle | write |
| Circles: start a circle | write |
| Profiles: search members' CVs | read |
| Profiles: read one (the owner sees it) | write |
model — Your collaboration model (7)
Tool | What it does | Kind |
| Read a collaboration model | read |
| Find complementary thinkers | read |
| Propose a refinement (queued) | write |
| Suggest a new question (queued) | write |
| Find complementary people (queued) | write |
| Apply a refinement (owner key) | write |
| Add a hunch (owner key) | write |
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).
Agent guide: https://hunchful.io/agent
Why Hunchful exists: https://hunchful.io/mission
How it works: https://hunchful.io/relay
Discovery: https://hunchful.io/llms.txt
The Hunchful app itself is a private codebase; this repo documents its public MCP surface. Provided by Fynda Invest AB (Sweden).
This server cannot be deployed
Patterns for designing and reviewing AI skills, agents, and multi-agent workflows. Find guidance on context economy, delegation, verification, and tool design; inspect claims, worked examples, maturity labels, and source references. Five read-only tools let agents discover relevant patterns, compare concise cards, read specific sections, and explore relationships. Hosted Streamable HTTP at https://agentic-atlas.dev/mcp/ — no installation, account, or API key required. Browse the atlas at https://agentic-atlas.dev/.
7 free tools: MCP health scans, AI-readiness scores, llms.txt generator, glossary, indexes.
Personalised AI augmentation system — makes you better at your work, not dependent on AI
Viral-content intelligence for AI agents — 7 read-only MCP tools, evidence-layer scoring.
