# Hunch Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Hunch

Paste a suspicious message and get a plain read on what stands out, plus the smallest safe next step.

- Record: https://musedirectory.ai/connector/hunch
- Category: Lifestyle
- Developer: Hunch (https://checkyourhunch.com/ai-assistants)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 82ms, checked 2026-11-09T02:16:13Z
- Endpoint: https://mcp.checkyourhunch.com/mcp
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-11-08T20:36:21Z)
- Source: Found in the official MCP Registry (io.github.dekeloco/hunch) https://registry.modelcontextprotocol.io/v0/servers?search=io.github.dekeloco%2Fhunch

Connects to Hunch's message-checking engine. Muse can review a suspicious text or email, point out what stands out, suggest the smallest safe next step, and check whether a phone number, domain, or email is listed on an organization's own site. It never calls a message safe or a sender a scammer.

Example request: "Does this text about a missed package delivery look like a scam?"

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Hunch to help me. It is a free service with an MCP server at https://mcp.checkyourhunch.com/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- check_message: Paste or forward a suspicious message. Hunch reads only the words you give it, on one frozen engine (the same engine behind the Hunch extension and site, running on our server), and tells you in plain language what stands out and the smallest next step you can take. It never tell
- check_official_channel: Ask whether a phone number, domain, email, or app is a channel an organization publishes on its own site. Hunch answers only from a public-source list (facts taken from each organization's own pages, with a source link and date, not confirmed to Hunch): anything not on it is repo

Screening checks:
- MCP handshake: pass (Answered in 110ms)
- Domain against threat feeds (Cloudflare security DNS): pass (mcp.checkyourhunch.com, checkyourhunch.com not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (2 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 68 days ago)
- AI review of purpose and tool behavior: pass (No concerns)