MCP server

Hunch

app.hunchsheet/hunch

Checked 26 Oct 2026, 08:29 UTC · It answered and asked for a sign-in

Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.

Website Source

At a glance

Type

MCP server

Publisher

hunchsheet.app (verified by the MCP Registry)

Status

Needs an API key

Tools

8

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http hunch https://hunchsheet.app/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.hunch]
url = "https://hunchsheet.app/mcp"

Gemini CLI

{"mcpServers":{"hunch":{"httpUrl":"https://hunchsheet.app/mcp"}}}

Cursor

{"mcpServers":{"hunch":{"url":"https://hunchsheet.app/mcp"}}}

VS Code

{"servers":{"hunch":{"type":"http","url":"https://hunchsheet.app/mcp"}}}

Antigravity

agy mcp add hunch https://hunchsheet.app/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"hunch","server_url":"https://hunchsheet.app/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"hunch","server_url":"https://hunchsheet.app/mcp"}

Needs an API key or token from its maker, usually added as a header in the setup.

Tools

• hunch_ask ~490 tokens
  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 leads, support tickets, reviews, survey answers or emails at once, for example "Is this lead a decision maker?" or "Is th
• hunch_balance ~177 tokens
  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 were skipped for lack of credits. On the keyless /mcp/try connection it reports the free sample rows left today.
• hunch_buy_credits Moves money · ~278 tokens
  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 5,000 rows (a key's first purchase), Top-up is $19 for 25,000 rows on a key that already paid. Credits never expire and
• hunch_get_key ~108 tokens
  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 with it). Limited to 2 keys per address per day. Treat the key like a password.
• hunch_multi ~458 tokens
  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 text at once, for example "Can they buy?", "Are they angry?", "Is it urgent?" on the same support ticket, for a fraction of
• hunch_pick ~523 tokens
  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, classify feedback, or tag leads by type, for example options ["billing: invoices and charges", "refund", "bug", "other"].
• hunch_quote ~289 tokens
  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 for 5,000 rows) and Top-up ($19 for 25,000 rows) applied. With a key it also says whether the credits on that key alread
• hunch_score ~505 tokens
  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 generated prose. Use it for sentiment ("angry|disappointed|neutral|happy|delighted"), fit scoring ("no fit|weak|good|perfect")

Browse

• Stripe tools
• Email
• Forms and surveys
• Payments
• Customer support

Related MCP servers

• Batru — Competitive Game Intelligence for AI Agents
  Live competitive-game predictions, meta data and decision tools for AI agents.
• cuttingfloor
  Video editing for AI agents: cuts, captions, audio, motion graphics, previews, and exports.
• AudioJev
  Audio in, calibrated probability per answer option out
• cribl-decision-1.0
  Calibrated probabilities over the options you supply
• Footballcharts
  Tables, results, fixtures, goal timing, season projections: 93 football leagues incl. lower tiers
• PolyBridge
  Calibrated probabilistic foresight for AI agents, powered by live prediction-market signal.
• Gero-4B
  Calibrated probabilities for decisions, no generated text
• Tanod ML
  Local ML: speech to text (SRT/VTT), text embeddings, reranking, similarity, entities, zero-shot.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/app.hunchsheet/hunch.svg)](https://aptlynx.net/servers/app.hunchsheet/hunch)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents