MCP serverapp.hunchsheet/hunch
Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.
Overview
Score?
UNRATED 0.220
of what a free look can see, on 7 looks
Looks
7
last 15 hr ago
Tools
8
changed 4 days ago
More info
URL
hunchsheet.app/mcp/try
streamable-http
Says it is
hunch 1.1.0
protocol 2025-06-18
In the record since
5 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.220 · highest on record 0.8561
Toolsfrom sha256:078c9d1db9…23b93e · +0 −0 4 days ago
| Tool | Schema |
|---|---|
| hunch_ask Judge a batch of short texts against one yes/no question and get back a calibrated probability (0 to 1) per text, not generated prose. Use it to score, tag, filter or triage many l |
input · output |
| hunch_balance Check how many Hunch credits are left on this key and how many have been used so far. Read-only, costs nothing. Call it before a large batch, or when a judging tool reports texts w |
input · output |
| hunch_buy_credits Returns a link the person can open to buy more credits with a card on Stripe. Nothing is charged until they finish paying on that page; you cannot pay for them. Starter is $29 for |
input · output |
| hunch_get_key Returns a Hunch key with 100 free rows, in this response, with no email and no card. For the keyless /mcp/try connection: pass the key as api_key to the other tools (or reconnect w |
input · output |
| hunch_multi Ask up to 10 yes/no questions about the same batch of texts in one call, one probability per question per text, not generated prose. Use it when several judgments read the same tex |
input · output |
| hunch_pick Sort a batch of short texts into one of your own categories and get back the chosen option plus how confident the model is, not generated prose. Use it to route support tickets, cl |
input · output |
| hunch_quote Free, no key needed. Give the number of texts (and questions per text) and get the credits the job needs and what it would cost in dollars, with the free 100-row key, Starter ($29 |
input · output |
| hunch_score Place a batch of short texts on your own ordered scale (2 to 10 levels, low to high) and get back a probability-weighted position, the most likely level, and confidence, not genera |
input · output |
Verify it yourself
npx teppi-check https://hunchsheet.app/mcp/trycurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M3NW5BX78Z5J4SV0CVE32XZ5