# noisefloor — is this number real? (pypi · noisefloor)

Is this number real, or is it noise? Peek-safe A/B tests, change detection, honest forecasts.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- pypi · `noisefloor`: 68/100 (this document), [markdown](https://verifymcp.io/servers/beepboop2025-noisefloor/noisefloor.md), [page](https://verifymcp.io/servers/beepboop2025-noisefloor/noisefloor)

## Channel facts

- Registry: `pypi`
- Package: `noisefloor`
- Version: `0.2.0`
- 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 2026-08-03.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 827 tokens (~137/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 89% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add beepboop2025-noisefloor -- uvx noisefloor
```

### Codex

```bash
codex mcp add beepboop2025-noisefloor -- uvx noisefloor
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "beepboop2025-noisefloor": {
      "type": "local",
      "command": [
        "uvx",
        "noisefloor"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add beepboop2025-noisefloor --command uvx --arg noisefloor
```

### Hermes

```yaml
mcp_servers:
  beepboop2025-noisefloor:
    command: "uvx"
    args: ["noisefloor"]
```

### Other

```json
{
  "mcpServers": {
    "beepboop2025-noisefloor": {
      "command": "uvx",
      "args": [
        "noisefloor"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 68, +29)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [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 regression] MCP protocol: unverified → fail
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 89
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [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: 0.1.2 → 0.2.0

### 2026-07-31 (score 39, +10)

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

### 2026-07-30 (score 29, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-29 (score 47, 0)

- [functional] Tool coverage: Tool coverage not yet verified: our sandbox run of this package did not complete, so we have no tool definitions to assess.
- [functional] Schema quality: Schema quality not yet verified: our sandbox run of this package did not complete, so we have no schema to assess.

### 2026-07-28 (score 47)

First indexed and scored.

## MCP tools (6)

### `ab_test` (~140 tokens)

Peek-safe A/B verdict

Can you call a winner on an A/B test yet? Uses anytime-valid confidence sequences, so it is SAFE TO RUN AFTER EVERY OBSERVATION — peeking does not inflate the false-positive rate the way a t-test or z-test does.

Input parameters:

- `a_label` (string)
- `a_successes` (integer, required): conversions in arm A
- `a_total` (integer, required): total observations in arm A
- `alpha` (number): error budget, default 0.05
- `b_label` (string)
- `b_successes` (integer, required): conversions in arm B
- `b_total` (integer, required): total observations in arm B

### `did_it_change` (~103 tokens)

Did this metric really change?

Did a metric actually change, or is the move noise? Detects both rises AND collapses against the metric's own history, with a stated false-alarm rate and no assumption about the distribution.

Input parameters:

- `half_life` (number): optional: readings after which old history counts half, for drifting metrics
- `two_sided` (boolean): detect drops as well as rises (default true)
- `values` (array, required): the metric's history, oldest first

### `forecast_next` (~67 tokens)

Calibrated next-value forecast

What should the next reading be, and within what range? Range adapts to the metric's recent volatility and stays valid even when the metric shifts.

Input parameters:

- `nominal` (number): range coverage, default 0.8
- `values` (array, required): the metric's history, oldest first

### `real_or_sampling` (~93 tokens)

Real effect, or sampling noise?

Did the metric move, or did the sample size underneath it move? Run this before reporting any RATE as a change — conversion rates, error rates and click-through all shift when the denominator shifts, for reasons that have nothing to do with the thing being measured.

Input parameters:

- `sample_sizes` (array, required): the denominator behind each reading, same order and length
- `values` (array, required): the metric's history, oldest first

### `score_forecasts` (~76 tokens)

Score past forecasts honestly

How good would these forecasts actually have been? Grades every prediction the tool would have made over the history, using only what was known at the time, and reports calibration plus the worst misses.

Input parameters:

- `nominal` (number): range coverage, default 0.8
- `values` (array, required): the metric's history, oldest first

### `which_metrics_matter` (~102 tokens)

Rank metrics by real signal

You watch many metrics; which genuinely stand out? Controls the false discovery rate across all of them at once, which per-metric thresholds do not: forty metrics each alerting wrongly 5% of the time means two false alarms every round.

Input parameters:

- `alpha` (number): false-discovery rate, default 0.1
- `evidence` (object, required): metric name -> evidence value, e.g. the 'evidence' field from did_it_change

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/beepboop2025-noisefloor/noisefloor#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 68
- 2026-08-01: 39
- 2026-07-31: 39
- 2026-07-30: 29
- 2026-07-29: 47
- 2026-07-28: 47

## Links

- PyPI project: https://pypi.org/project/noisefloor/
- Socket report: https://socket.dev/pypi/package/noisefloor
- Repository: https://github.com/beepboop2025/noisefloor
- Changelog RSS feed: https://verifymcp.io/servers/beepboop2025-noisefloor/noisefloor/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/beepboop2025-noisefloor/noisefloor/changelog.json
- HTML version of this page: https://verifymcp.io/servers/beepboop2025-noisefloor/noisefloor