io.github.beepboop2025/noisefloor

up checked 2026-11-11T05:37:50.116Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

NoiseFloor — market attention and evidence checks

Publisher-provided description

Offline market diagnostics, news repetition, data coverage and statistical checks for AI agents.

Summary by lookupd

Runs offline statistical checks on market series, headlines, and metrics: A/B tests, forecasts, anomaly monitoring, and triage for review.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http noisefloor https://api.seiche.info/noisefloor/mcp

Claude Code, pypi package (stdio)

claude mcp add noisefloor -- uvx noisefloor

Codex, remote (streamable-http)

codex mcp add noisefloor --url https://api.seiche.info/noisefloor/mcp

Codex, pypi package (stdio)

codex mcp add noisefloor -- uvx noisefloor

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "noisefloor": {
      "url": "https://api.seiche.info/noisefloor/mcp"
    }
  }
}

Cursor, pypi package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "noisefloor": {
      "command": "uvx",
      "args": [
        "noisefloor"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (10 tools)

Publisher-provided text

• ab_test Compare two cumulative binary-outcome experiment arms to decide whether either success rate is higher. Use for conversions or other Bernoulli outcomes with cons
• did_it_change Scan one chronological numeric metric for departures from its own preceding observations, using a descriptive rank-based Shiryaev-Roberts monitor. Use this for
• dyson_reference Generate a seeded synthetic real-symmetric Brownian-matrix path to illustrate eigenvalue repulsion (beta=1). Use for reproducible numerical education or researc
• forecast_next Estimate the next observation of one numeric series using the last value as a point forecast and adaptive historical absolute-error quantiles for an empirical i
• market_assessment Build a source-aware review queue for caller-supplied market series at an explicit UTC as_of cutoff, checking moves, volatility, missing data and measurement co
• narrative_triage Deduplicate and prioritize a caller-supplied headline collection for human or agent review at a UTC as_of cutoff. Use for wording repetition, entity focus and p
• real_or_sampling Review whether the latest numeric metric departure persists after accounting for its historical linear association with measurement sample size. Use when both a
• score_forecasts Backtest NoiseFloor's own one-step forecast on chronological historical prefixes, issuing before observing and then updating without hindsight. Use to evaluate
• spectral_assessment Analyze shared correlation structure and rolling concentration in a caller-defined comparable panel. Use for research on shared movements across at least two se
• which_metrics_matter Rank a named board of nonnegative evidence scores for review. By default valid_evalues=false: arbitrary nonnegative scores are ranked descriptively and selected

Details

• Version: 0.4.3
• Transports: streamable-http, stdio
• Uptime (7 days): 100%
• Median latency: 973 ms
• First indexed: 2026-11-01T09:21:38.608Z
• Last seen in registry: 2026-11-01T09:21:39.006Z
• Repository: https://github.com/beepboop2025/noisefloor

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.beepboop2025/noisefloor.svg)](https://lookupd.com/servers/io.github.beepboop2025/noisefloor)

• 62141 servers
• Last crawl: 2026-11-11T18:39:04.612Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp