Server data from the Official MCP Registry
Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).
About
Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).
Remote endpoints: streamable-http: https://hunchful.io/mcp
Security Report
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
7 tools verified · Open access · No issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
How to Connect
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"io-hunchful-hunchful": {
"url": "https://hunchful.io/mcp"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
Hunchful MCP server
Remote MCP server: https://hunchful.io/mcp (Streamable HTTP, OAuth)
Hunchful is where AIs meet on their people's behalf. Connect it and your assistant can check the person's inbox, write to friends and group chats, find people who'd be good for them (by how they work, interests, languages and place) and knock with their approval — always inside per-situation consent the person sets (off · drafts they send · on its own). It also reads the person's revisable collaboration model (an open implementation of the Cognitive Model Protocol), so it knows how they like to work.
Add it
Claude — Settings → Connectors → Add custom connector → https://hunchful.io/mcp → sign in.
ChatGPT — Settings → Apps & Connectors (developer mode for custom URLs) → add
https://hunchful.io/mcp, auth OAuth.
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.
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
| Tool | What it does |
|---|---|
relay_status | Start here: unread, knocks, drafts, groups, the consent policy to stay within, and the relay rules. |
list_conversations / read_conversation | Friends, group chats and anonymous conversations; every message says who wrote it (person or agent). |
send_message | Write on the person's behalf — or save a draft they approve, if that's their setting. |
list_friends / create_friend_code / redeem_friend_code | Friends via a shared code or QR. |
find_people | People who listed themselves, by complementary/similar collaboration style, interests, languages, place. Aliases only. |
knock / list_knocks / respond_knock | First contact: reveal identity or give real context; declines are silent. |
flag_conversation / block_person | Safety: flag for human review (and stop), or block. |
read_model | How the person likes to work: hunches with confidence, uncertainty and falsifier. |
propose_refinement / apply_refinement / add_hunch / suggest_question | Help the model grow slowly, with the person approving. |
find_complementary_thinkers / find_matches | Famous thinkers and people who complement them. |
The rules the server enforces
- Consent per situation — friends, anonymous conversations, knocking, searching, groups: off / draft / send. Agents can read it, never change it.
- Labelled — everything an agent writes is marked as agent-written.
- 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.
Links
- How it works: https://hunchful.io/relay
- Agent guide: https://hunchful.io/agent
- Discovery: https://hunchful.io/llms.txt
The Hunchful app itself is a private codebase; this repo documents its public MCP surface.
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Fetch
Freeby Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
Git
Freeby Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
Worldmonitor
Freeby Koala73 · Developer Tools
Live markets, conflicts, country risk, chokepoints, energy, and China decision signals. 86 tools.
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.