# gut (pypi · gutfeel-mcp)

Judgment calls on small, cheap models: is this spam, which team, how urgent. YES, NO or UNSURE.

- Trust score: 76/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- pypi · `gutfeel-mcp`: 76/100 (this document), [markdown](https://verifymcp.io/servers/kungie-gut/gutfeel-mcp.md), [page](https://verifymcp.io/servers/kungie-gut/gutfeel-mcp)

## Channel facts

- Registry: `pypi`
- Package: `gutfeel-mcp`
- Version: `0.8.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-10-23.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs uv_build at install time, a recognised build step with no custom scripting around it.
  - 1 of 35 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Kungie/gut).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 9 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 802 tokens (~200/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

gut runs locally as a PyPI package, launched with uvx gutfeel-mcp. 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 kungie-gut -- uvx gutfeel-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "kungie-gut": {
      "command": "uvx",
      "args": [
        "gutfeel-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "kungie-gut": {
      "command": "uvx",
      "args": [
        "gutfeel-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add kungie-gut -- uvx gutfeel-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kungie-gut": {
      "type": "local",
      "command": [
        "uvx",
        "gutfeel-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add kungie-gut --command uvx --arg gutfeel-mcp
```

### Hermes

```yaml
mcp_servers:
  kungie-gut:
    command: "uvx"
    args: ["gutfeel-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "kungie-gut": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "gutfeel-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add kungie-gut -t stdio -c uvx -a gutfeel-mcp
```

### Other

```json
{
  "mcpServers": {
    "kungie-gut": {
      "command": "uvx",
      "args": [
        "gutfeel-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-10-22 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 72, +23)

- [security regression] Malware scan: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.50
- [functional improvement] MCP protocol: unverified → pass
- [functional] Package version: 0.8.0 → 0.8.2

### 2026-10-13 (score 49, 0)

- [security regression] Malware scan: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [security] Tool safety: Tool safety not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.47
- [functional improvement] MCP protocol: unverified → pass
- [functional] Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet.
- [functional] Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Package version: 0.8.1 → 0.8.2
- [functional] Package version: 0.8.0 → 0.8.1

### 2026-10-12 (score 49, −31)

- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no schema to compare.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.8.0 → 0.8.1

### 2026-10-03 (score 80, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (4)

### `likely` (~150 tokens)

Judge whether a claim is true of a text. Answers yes or no with the model's
probability that the claim is true -- or unsure, when ask_human is set.

Input parameters:

- `ask_human` (boolean): Allow the outcome `unsure` when the model cannot tell. Off by default.
- `lean`: Which way to err when unsure is not allowed.
- `question` (string, required): A short claim about the text, e.g. "asks for a refund". Not an open question.
- `stakes`: How sure the model must be before an answer counts. Needs ask_human.
- `subject` (string, required): The text to judge: an email, a comment, a diff.

### `classify` (~161 tokens)

Pick the option that fits a text best: a team, a topic, a language, an intent. Answers
with the chosen label, every option's probability and a confidence.

Input parameters:

- `ask_human` (boolean): Allow the outcome `unsure` when the model cannot tell. Off by default.
- `options` (required): The categories: {label: description}, or a list of labels. Include a catch-all such as "other", or every text is forced into one of them.
- `question`: What to decide, if the options do not say it.
- `stakes`: How sure the model must be before an answer counts. Needs ask_human.
- `subject` (string, required): The text to judge: an email, a comment, a diff.

### `rate` (~144 tokens)

Rate a text on an ordered scale such as urgency or severity. Answers with a score,
which can fall between levels, the nearest level and a confidence.

Input parameters:

- `ask_human` (boolean): Allow the outcome `unsure` when the model cannot tell. Off by default.
- `levels` (array, required): Between 2 and 10 level descriptions, in order; the first is level 0.
- `question`: What to rate, if the levels do not say it.
- `stakes`: How sure the model must be before an answer counts. Needs ask_human.
- `subject` (string, required): The text to judge: an email, a comment, a diff.

### `each` (~151 tokens)

Ask the same question about many texts at once: likely with just a question, classify
with options, rate with levels. Far faster than one call per text.

Input parameters:

- `ask_human` (boolean): Allow the outcome `unsure` when the model cannot tell. Off by default.
- `levels`: A scale, as for rate.
- `options`: Categories, as for classify.
- `question`: A claim, as for likely. Alone, it asks likely; with options or levels, it says what to decide.
- `stakes`: How sure the model must be before an answer counts. Needs ask_human.
- `subjects` (array, required): The texts to judge, all with the same question.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/kungie-gut/gutfeel-mcp#diagnostics

## Score history

- 2026-10-23: 76
- 2026-10-22: 76
- 2026-10-21: 75
- 2026-10-20: 75
- 2026-10-19: 74
- 2026-10-18: 74
- 2026-10-17: 73
- 2026-10-16: 73
- 2026-10-15: 72
- 2026-10-14: 72
- 2026-10-13: 49
- 2026-10-12: 49
- 2026-10-06: 80
- 2026-10-04: 80
- 2026-10-03: 80
- 2026-10-02: 65
- 2026-10-01: 65
- 2026-09-30: 80
- 2026-09-29: 65

## Common questions

### What is the gut MCP server?

gut is an MCP server listed in the public MCP registry as io.github.Kungie/gut. Judgment calls on small, cheap models: is this spam, which team, how urgent. YES, NO or UNSURE. This page covers its PyPI package (gutfeel-mcp).

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

gut scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. Its build provenance is signed and verified. 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 gut MCP server expose?

gut exposes 4 tools: likely, classify, rate, each. Their descriptions and schemas cost roughly 606 tokens of context every time the server is loaded.

### Is the gut MCP server still maintained?

gut is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the gut MCP server under?

gut declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/gutfeel-mcp/
- Socket report: https://socket.dev/pypi/package/gutfeel-mcp
- Repository: https://github.com/Kungie/gut
- Website: https://gutpy.dev/docs/mcp.html
- Changelog RSS feed: https://verifymcp.io/servers/kungie-gut/gutfeel-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/kungie-gut/gutfeel-mcp.json
- HTML version of this page: https://verifymcp.io/servers/kungie-gut/gutfeel-mcp