Hunch

app.hunchsheetPublished by hunchsheet.appOfficial publisherv1.1.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Hunch returns calibrated numeric judgments about text — yes/no probabilities, picks from your options, or scores — so an assistant can sort, filter and count…

What you can do
  • Ask a yes/no question about each text and get the probability of yes
  • Pick one option from your own list for each text, with confidence
  • Score each text on your own levels, returning the most likely level and confidence
  • Ask up to 10 yes/no questions per text in one call
  • Check remaining credits, get a cost quote before running a job, and get a checkout link for buying credits
When to use it
Useful when an assistant needs consistent, comparable judgments over lists of short texts such as leads, support tickets, reviews, survey answers or emails, and needs numbers it can sort, filter or count rather than free-form text.
Requirements
Remote Streamable HTTP endpoint at hunchsheet.app; no local package. An OAuth sign-in or an Authorization bearer key is required; a keyless try endpoint allows ten texts a day, and a free key covers 100 rows. Paid credits cost $29 per 5,000 rows.
Before you install
The Authorization bearer key is a secret and should be kept out of files where possible. Paid usage consumes credits; the assistant can only return a checkout link and cannot pay. Texts and questions in each call are sent to the Hunch server and to TypeSafe to compute answers, though not stored. It judges text only, not arithmetic, counting or dates, and English works best.

Installation

In SourceWeft

  1. Open Hunch in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/app.hunchsheet%2Fhunch/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

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

README

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

ToolReturns
hunch_askThe probability of yes, 0 to 1, for each text
hunch_pickOne option from your list for each text, with its confidence
hunch_scoreA position on your levels (0 to n-1), the most likely level, and its confidence
hunch_multiOne probability per question for each text, up to 10 questions
hunch_balanceCredits left on your key
hunch_quoteCredits and dollars a job needs, before you run it. Free, no key needed
hunch_buy_creditsA checkout link for the person to open. The assistant cannot pay for them
hunch_get_keyKeyless /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

/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:

CommandWrites 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.

Source: README.md at commit e810338

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v1.1.0LatestSep 30, 2026
  2. v1.0.0Sep 28, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts