# Hunch (remote · hunchsheet.app)

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

- Trust score: 39/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-07

## Components

- remote · `hunchsheet.app`: 39/100 (this document), [markdown](https://verifymcp.io/servers/app-hunchsheet-hunch/hunchsheet.md), [page](https://verifymcp.io/servers/app-hunchsheet-hunch/hunchsheet)
- remote · `hunchsheet.app`: 0/100, [markdown](https://verifymcp.io/servers/app-hunchsheet-hunch/mcp-api-key.md), [page](https://verifymcp.io/servers/app-hunchsheet-hunch/mcp-api-key)
- remote · `hunchsheet.app`: 86/100, [markdown](https://verifymcp.io/servers/app-hunchsheet-hunch/mcp-try.md), [page](https://verifymcp.io/servers/app-hunchsheet-hunch/mcp-try)

## Channel facts

- Endpoint: `https://hunchsheet.app/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-07.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Tool Safety**: 0/100
  - Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 6 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Hunch MCP server?

Hunch is a hosted endpoint at https://hunchsheet.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

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

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-hunchsheet-hunch": {
      "type": "remote",
      "url": "https://hunchsheet.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-hunchsheet-hunch --url 'https://hunchsheet.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-hunchsheet-hunch:
    url: "https://hunchsheet.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-hunchsheet-hunch": {
      "Transport": "http",
      "Url": "https://hunchsheet.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-hunchsheet-hunch -t streamable-http -u 'https://hunchsheet.app/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-06 (score 39, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-29 (score 0)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → unverified
- [security improvement] Authorization: partial → pass
- [security] First check of Authorization: pass
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Schema quality: unverified

### 2026-09-28 (score 0)

First indexed and scored.

## MCP tools (5)

### `hunch_ask` (~246 tokens)

Hunch: yes/no probability

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; answers are cached 6 hours). 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.

Input parameters:

- `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.
- `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 cal…

Output parameters:

- `charged` (integer): Credits spent on this call.
- `credits` (integer): Credits left on the key after this call.
- `results` (array)

### `hunch_pick` (~273 tokens)

Hunch: pick one option

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.

Input parameters:

- `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. What is being decided, e.g. "Which category does this ticket belong to?". Defaults to "Which option best describes this text?".
- `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 cal…

Output parameters:

- `charged` (integer)
- `credits` (integer)
- `results` (array)

### `hunch_score` (~265 tokens)

Hunch: score on a scale

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.

Input parameters:

- `levels` (array, required): The scale, low to high, 2 to 10 levels, e.g. ["angry", "disappointed", "neutral", "happy", "delighted"]. Each may be "label: description".
- `question` (string, required): What is being scored, e.g. "How does the reviewer feel about the product overall?".
- `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 cal…

Output parameters:

- `charged` (integer)
- `credits` (integer)
- `results` (array)

### `hunch_multi` (~225 tokens)

Hunch: several yes/no questions at once

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.

Input parameters:

- `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?"].
- `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 cal…

Output parameters:

- `charged` (integer)
- `credits` (integer)
- `results` (array)

### `hunch_balance` (~56 tokens)

Hunch: check credits

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.

Output parameters:

- `credits` (integer): Credits left on the key.
- `used` (integer): Credits used on this key so far, lifetime.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-hunchsheet-hunch/hunchsheet#diagnostics

## Score history

- 2026-11-07: 39
- 2026-11-06: 39
- 2026-11-05: 39
- 2026-11-04: 39
- 2026-11-03: 39
- 2026-11-02: 39
- 2026-11-01: 39
- 2026-10-31: 39
- 2026-10-30: 39
- 2026-10-29: 39
- 2026-10-28: 39
- 2026-10-27: 39
- 2026-10-26: 39
- 2026-10-25: 39
- 2026-10-24: 39
- 2026-10-23: 39
- 2026-10-22: 39
- 2026-10-21: 39
- 2026-10-20: 39
- 2026-10-19: 39
- 2026-10-18: 39
- 2026-10-17: 39
- 2026-10-16: 39
- 2026-10-15: 39
- 2026-10-14: 39
- 2026-10-13: 39
- 2026-10-12: 39
- 2026-10-10: 39
- 2026-10-07: 39
- 2026-10-04: 39

## Common questions

### What is the Hunch MCP server?

Hunch is an MCP server listed in the public MCP registry as app.hunchsheet/hunch. Calibrated judgments for text: yes/no probabilities, picks from your options, or scores. This page covers its hosted endpoint (https://hunchsheet.app/mcp).

### Is the Hunch MCP server safe to use?

Hunch scores 39 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Hunch MCP server expose?

Hunch exposes 5 tools: hunch_ask, hunch_pick, hunch_score, hunch_multi, hunch_balance. Their descriptions and schemas cost roughly 1,065 tokens of context every time the server is loaded.

### Does the Hunch MCP server require authentication?

Yes. Hunch asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Hunch MCP server still maintained?

Hunch is still listed as active in the MCP registry. We last reached this channel on 7 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Hunch MCP server?

VerifyMCP ran 5 checks on Hunch, covering TLS certificate, Authorization, HTTPS, HSTS header and 1 more. 6 items could not be completed, a gap on our side rather than a finding about Hunch: Transport, Schema quality, Stability, Tool coverage and 2 more. 6 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://hunchsheet.app/mcp
- Authorisation metadata: https://hunchsheet.app/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/Eddy1919/hunch-mcp
- Website: https://hunchsheet.app/connectors
- Changelog RSS feed: https://verifymcp.io/servers/app-hunchsheet-hunch/hunchsheet.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-hunchsheet-hunch/hunchsheet/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/app-hunchsheet-hunch/hunchsheet.json
- HTML version of this page: https://verifymcp.io/servers/app-hunchsheet-hunch/hunchsheet