Hunch

Official5 tools

by Eddy1919

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

app.hunchsheet/hunch Model Context Protocol (MCP) Server

The app.hunchsheet/hunch MCP server provides calibrated judgments for text. It supports returning yes/no probabilities, selecting answers from user-provided options, or generating scores based on the input text. The server is identified by the slug app-hunchsheet-hunch and described as “Calibrated judgments for text.”

🛠️ Key Features

Calibrated judgments for text
Yes/no probability outputs
Option-based picks from your options
Score outputs

🚀 Use Cases

Estimating whether text content meets a yes/no criterion
Choosing among predefined options for text
Producing numeric scores for text inputs

⚡ Developer Benefits

Predictable output modes: yes/no probabilities, option picks, or scores
Suitable for pipelines that need structured judgment results

⚠️ Limitations

No additional capabilities, tool details, or topics are provided in the available server data

Topics

claude-codeclaude-code-pluginexcelgemini-cligemini-cli-extensiongoogle-sheetsmcpmcp-servermodel-context-protocoltext-classification

Captured live from the server via tools/list.

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 leads, support tickets, reviews, survey answers or emails at once, for example "Is this lead a decision maker?" or "Is this email urgent?". Costs 1 credit per answered text (blank texts and texts repeated elsewhere in the same call are free; the same text asked again in a later call is charged again). Limits: the model reads the text only, no math, counting or dates; English works best; put the full definition of what counts as yes inside the question, since the model sees nothing else.

Parameters2

texts	array	required	Short texts to judge (leads, tickets, reviews, survey answers, emails, ...), one answer per text. Blank entries and texts repeated elsewhere in the same call cost nothing. Chunked internally into calls of 40.
question	string	required	A yes/no question, e.g. "Is this lead a decision maker who can approve a purchase without asking someone else?". Put the full definition of yes/no in the question text.

Raw schema

{
  "type": "object",
  "properties": {
    "texts": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 500,
      "description": "Short texts to judge (leads, tickets, reviews, survey answers, emails, ...), one answer per text. Blank entries and texts repeated elsewhere in the same call cost nothing. Chunked internally into calls of 40."
    },
    "question": {
      "type": "string",
      "minLength": 1,
      "description": "A yes/no question, e.g. \"Is this lead a decision maker who can approve a purchase without asking someone else?\". Put the full definition of yes/no in the question text."
    }
  },
  "required": [
    "texts",
    "question"
  ],
  "additionalProperties": false
}

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, classify feedback, or tag leads by type, for example options ["billing: invoices and charges", "refund", "bug", "other"]. Costs 1 credit per answered text (blanks and duplicates in the same call are free). Limits: 2 to 255 options, each "label" or "label: description" to disambiguate a short label; the model reads the text only, no math, counting or dates, English works best.

Parameters3

texts	array	required	Short texts to judge (leads, tickets, reviews, survey answers, emails, ...), one answer per text. Blank entries and texts repeated elsewhere in the same call cost nothing. Chunked internally into calls of 40.
options	array	required	The options to choose from, 2 to 255 of them. Each is "label" or "label: description" when the label alone is ambiguous, e.g. "billing: invoices and charges".
question	string	optional	Optional. What is being decided, e.g. "Which category does this ticket belong to?". Defaults to "Which option best describes this text?".

Raw schema

{
  "type": "object",
  "properties": {
    "texts": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 500,
      "description": "Short texts to judge (leads, tickets, reviews, survey answers, emails, ...), one answer per text. Blank entries and texts repeated elsewhere in the same call cost nothing. Chunked internally into calls of 40."
    },
    "options": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 2,
      "maxItems": 255,
      "description": "The options to choose from, 2 to 255 of them. Each is \"label\" or \"label: description\" when the label alone is ambiguous, e.g. \"billing: invoices and charges\"."
    },
    "question": {
      "type": "string",
      "description": "Optional. What is being decided, e.g. \"Which category does this ticket belong to?\". Defaults to \"Which option best describes this text?\"."
    }
  },
  "required": [
    "texts",
    "options"
  ],
  "additionalProperties": false
}

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 generated prose. Use it for sentiment ("angry|disappointed|neutral|happy|delighted"), fit scoring ("no fit|weak|good|perfect"), or any low-to-high rating. Costs 1 credit per answered text (blanks and duplicates in the same call are free). Limits: the model reads the text only, no math, counting or dates, English works best, and the question should say what is being scored.

Parameters3

texts	array	required	Short texts to judge (leads, tickets, reviews, survey answers, emails, ...), one answer per text. Blank entries and texts repeated elsewhere in the same call cost nothing. Chunked internally into calls of 40.
question	string	required	What is being scored, e.g. "How does the reviewer feel about the product overall?".
levels	array	required	The scale, low to high, 2 to 10 levels, e.g. ["angry", "disappointed", "neutral", "happy", "delighted"]. Each may be "label: description".

Raw schema

{
  "type": "object",
  "properties": {
    "texts": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 500,
      "description": "Short texts to judge (leads, tickets, reviews, survey answers, emails, ...), one answer per text. Blank entries and texts repeated elsewhere in the same call cost nothing. Chunked internally into calls of 40."
    },
    "question": {
      "type": "string",
      "minLength": 1,
      "description": "What is being scored, e.g. \"How does the reviewer feel about the product overall?\"."
    },
    "levels": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 2,
      "maxItems": 10,
      "description": "The scale, low to high, 2 to 10 levels, e.g. [\"angry\", \"disappointed\", \"neutral\", \"happy\", \"delighted\"]. Each may be \"label: description\"."
    }
  },
  "required": [
    "texts",
    "question",
    "levels"
  ],
  "additionalProperties": false
}

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 text at once, for example "Can they buy?", "Are they angry?", "Is it urgent?" on the same support ticket, for a fraction of the tokens of separate calls. Costs 1 credit per answered question per text (blanks and duplicate texts are free). Limits: the model reads the text only, no math, counting or dates, English works best, and each question needs its own definition of yes inside it.

Parameters2

texts	array	required	Short texts to judge (leads, tickets, reviews, survey answers, emails, ...), one answer per text. Blank entries and texts repeated elsewhere in the same call cost nothing. Chunked internally into calls of 40.
questions	array	required	Up to 10 yes/no questions, each answered once per text, e.g. ["Can they buy?", "Are they angry?", "Is it urgent?"].

Raw schema

{
  "type": "object",
  "properties": {
    "texts": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 500,
      "description": "Short texts to judge (leads, tickets, reviews, survey answers, emails, ...), one answer per text. Blank entries and texts repeated elsewhere in the same call cost nothing. Chunked internally into calls of 40."
    },
    "questions": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 10,
      "description": "Up to 10 yes/no questions, each answered once per text, e.g. [\"Can they buy?\", \"Are they angry?\", \"Is it urgent?\"]."
    }
  },
  "required": [
    "texts",
    "questions"
  ],
  "additionalProperties": false
}

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 were skipped for lack of credits.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

README.md5 KBView on GitHub

Hunch MCP

Hunch gives your AI assistant calibrated judgments about text. For each text you send, it returns the probability that the answer to a yes/no question is yes, one option from your own list, a score on your own scale, or several yes/no answers at once. The answers come from Jev, TypeSafe's System One model, which returns numbers instead of generated text, so your assistant can sort, filter and count them.

The server is hosted at https://hunchsheet.app/mcp (Streamable HTTP). This repo holds the install files for Claude Code and Gemini CLI. Setup for Claude, ChatGPT, Cursor and VS Code is at hunchsheet.app/connectors.

Any agent, one line

bash

npx add-mcp https://hunchsheet.app/mcp -y

That adds the server to every agent it finds on your machine (Claude Code, Cursor, VS Code, Codex, Gemini CLI and more). Sign in when the agent asks, or press Start with 100 free rows on the sign-in page: no email, no card. To try Hunch with no account at all, use https://hunchsheet.app/mcp/try instead: ten texts a day are free. Install lines for each client: hunchsheet.app/install. How agents use it: hunchsheet.app/agents.

Tools

Tool	Returns
`hunch_ask`	The probability of yes, 0 to 1, for each text
`hunch_pick`	One option from your list for each text, with its confidence
`hunch_score`	A position on your levels (0 to n-1), the most likely level, and its confidence
`hunch_multi`	One probability per question for each text, up to 10 questions
`hunch_balance`	Credits left on your key
`hunch_quote`	Credits and dollars a job needs, before you run it. Free, no key needed
`hunch_buy_credits`	A checkout link for the person to open. The assistant cannot pay for them
`hunch_get_key`	Keyless `/mcp/try` connection only: a key with 100 free rows, no email

Good for leads, support tickets, reviews, survey answers, emails and any list of short texts you want judged the same way. It judges text only: no arithmetic, counting or dates. English works best. Put the definition inside the question, for example "Can this person approve a software purchase without asking someone else?" instead of "Is this a decision maker?".

Get a key

The form at hunchsheet.app emails a key with 100 free rows. No inbox? The sign-in page has a free-rows button, and an agent can call hunch_get_key on /mcp/try. After that, 5,000 rows cost $29 and credits never expire. One credit per answered text per question. Blank texts and repeats in the same call are free.

Claude Code

code

/plugin marketplace add Eddy1919/hunch-mcp
/plugin install hunch@hunch-mcp

Then run /mcp, pick hunch and choose Authenticate. A hunchsheet.app page opens in your browser: paste your key and click Connect. The key never goes into a file, and Claude Code renews the sign-in on its own.

The plugin adds the server, a skill that tells Claude when to use each tool, and three commands for CSV files:

Command	Writes back, for each row
`/hunch:hunch-check <file.csv> <column> <yes/no question>`	The probability of yes
`/hunch:hunch-tag <file.csv> <column> <label1,label2,...> [question]`	One of your labels, with its confidence
`/hunch:hunch-score <file.csv> <column> <question> <level1,...,levelN>`	A level from your scale, with its confidence

For scripts or CI where no browser is available, add the server with the key in a header instead of installing the plugin:

bash

claude mcp add --transport http hunch https://hunchsheet.app/mcp --header "Authorization: Bearer hunch_your_key_here"

Gemini CLI

bash

gemini extensions install https://github.com/Eddy1919/hunch-mcp

Gemini CLI asks for your key during install and stores it as a sensitive setting.

Claude, ChatGPT, Cursor and VS Code

Claude (claude.ai and Claude Desktop): add a custom connector with the URL https://hunchsheet.app/mcp, then sign in with your key when Claude opens Hunch's page.
ChatGPT: in developer mode, create a connector with the same URL and sign in the same way.
Cursor and VS Code: one-click install buttons on hunchsheet.app/connectors.

Data

The texts and question in a tool call go to the Hunch server and to TypeSafe to compute the answer, and are not stored. Details at hunchsheet.app/privacy.

License

The files in this repo are MIT licensed. The Hunch service has its own terms.

Install

Tools (5)

hunch_askhunch_pickhunch_scorehunch_multihunch_balance

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://hunchsheet.app/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "hunch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://hunchsheet.app/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

app.hunchsheet/hunch Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

hunch_ask

hunch_pick

hunch_score

hunch_multi

hunch_balance

Hunch MCP

Any agent, one line

Tools

Get a key

Claude Code

Gemini CLI

Claude, ChatGPT, Cursor and VS Code

Data

License

Install

Remote endpoint

Related servers