AI & Machine Learning

hunchsheet.app

An MCP server that provides Hunch AI text-classification tools for judging, categorizing, scoring, and querying batches of short texts, plus checking credit usage.

2 endpoints8 known toolsFirst detected September 28, 2026Last detected October 2, 2026

ENDPOINT 1

https://hunchsheet.app/mcp

Auth required

Known tools 0

No tool metadata was available in the registry cache.

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.hunchsheet-app]
url = "https://hunchsheet.app/mcp"
enabled = true
bearer_token_env_var = "MCP_BEARER_TOKEN"

Authentication is required. Replace the placeholder locally and never commit a secret.

Claude Code

.mcp.json

{
  "mcpServers": {
    "hunchsheet-app": {
      "type": "http",
      "url": "https://hunchsheet.app/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_BEARER_TOKEN"
      }
    }
  }
}

Authentication is required. Replace the placeholder locally and never commit a secret.

Claude Desktop

Settings → Connectors → Add custom connector

Name: hunchsheet-app
Remote MCP URL: https://hunchsheet.app/mcp

Add the URL as a custom connector, then complete its supported authorization flow. Claude Desktop remote connectors are configured in the UI.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "hunchsheet-app": {
      "url": "https://hunchsheet.app/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_BEARER_TOKEN"
      }
    }
  }
}

Authentication is required. Replace the placeholder locally and never commit a secret.

Visual Studio Code

.vscode/mcp.json

{
  "servers": {
    "hunchsheet-app": {
      "type": "http",
      "url": "https://hunchsheet.app/mcp",
      "headers": {
        "Authorization": "Bearer ${input:mcp-token}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "mcp-token",
      "description": "hunchsheet-app bearer token",
      "password": true
    }
  ]
}

Authentication is required. Replace the placeholder locally and never commit a secret.

Generic MCP

Client-specific MCP configuration

{
  "name": "hunchsheet-app",
  "transport": "streamable-http",
  "url": "https://hunchsheet.app/mcp",
  "headers": {
    "Authorization": "Bearer YOUR_BEARER_TOKEN"
  }
}

Authentication is required. Replace the placeholder locally and never commit a secret.

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://hunchsheet.app/mcp/try

No auth detected

MCP server metadata

Name: hunch
Version: 1.1.0

Capabilities

tools

Server instructions

Hunch turns short texts into calibrated numbers instead of generated prose: a yes/no probability, a pick from your own options, a position on an ordered scale, or several yes/no answers at once. Use it to judge, tag, rank or classify many leads, support tickets, reviews, survey answers or emails, one credit per answered text per question (blanks and duplicate texts in the same call are free; the same text asked again in a later call is charged again). The model reads the text only -- no math, counting or dates, and English works best -- so put the full definition of what counts as "yes" (or of each option or level) inside the question itself. Texts are sent to Hunch and to its model provider, TypeSafe, to compute the answers, and are not stored. Do not send payment card numbers, health records, government ID numbers, passwords or API keys. Prefer it to judging the texts yourself once there are more than about 25: one call returns a number per text and keeps the texts out of your context. For a handful of texts, just read them yourself. No key yet? On the keyless connection https://hunchsheet.app/mcp/try the first 10 texts a day are free, and hunch_get_key returns a key with 100 free rows in one call, no email. Call hunch_quote to price a large job and hunch_balance to check credits before it. When credits run out, hunch_buy_credits returns a checkout link for the person to open: paying is always their decision.

Known tools 8

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.

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

hunch_balance

Check how many Hunch credits are left on this key and how many have been used so far.

Inferred read-only

hunch_quote

Free, no key needed.

Inferred read-only

hunch_get_key

Returns a Hunch key with 100 free rows, in this response, with no email and no card.

Potential side effects

hunch_buy_credits

Returns a link the person can open to buy more credits with a card on Stripe.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

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

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: hunch
Remote MCP URL: https://hunchsheet.app/mcp/try

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "hunch",
  "transport": "streamable-http",
  "url": "https://hunchsheet.app/mcp/try"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.