Skip to content

ideaudit

by inite.studio · remote · local (npm) · no sign-in to list tools · v1.1.0 · published by studio.inite

The scoring behind an audit allowed to say no. Twenty deterministic tools, offline, no account.

Deletes · 1Changes · 16
CompareRegistry entry

21 tools: 1 can delete or cancel things, 16 change things and 4 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http ideaudit-tools https://api.inite.studio/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

21 tools

Deletes or cancels 1Claude Code: deny
  • derive_kill_criteriaDerive a falsifiable, data-driven list of kill criteria from upstream signals — the outputs of validate_unit_economics and compute_dealbreakers_v2, plus an ICP drift count.No findings

    Why it is in this group

    • The name "derive_kill_criteria" says "kill": a word for removing or ending something.
    Description, as the server wrote it
    Derive a falsifiable, data-driven list of kill criteria from upstream signals — the outputs of validate_unit_economics and compute_dealbreakers_v2, plus an ICP drift count. Returns one row per rule with {rule, threshold, status, evidence?}, where status is tripped_now / monitor / cleared. Replaces prose kill criteria, which are tautologies that can never fire.
Changes things 16Claude Code: ask
  • compute_barrierCompute barrier_score (0-24) + label (PRISTINE/OPEN/COMPETITIVE/CROWDED) from competitor counts + SERP noise fraction.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute barrier_score (0-24) + label (PRISTINE/OPEN/COMPETITIVE/CROWDED) from competitor counts + SERP noise fraction.
  • compute_budget_proofCompute budget_proof_score (0-10) + label (STRONG/CONFIRMED/WEAK/ABSENT) + purchase_intent_pct from pricing hits + review-site hits + intent mentions.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute budget_proof_score (0-10) + label (STRONG/CONFIRMED/WEAK/ABSENT) + purchase_intent_pct from pricing hits + review-site hits + intent mentions.
  • compute_build_complexityCompute build_complexity_penalty (0-10, higher = worse) + per-factor breakdown.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute build_complexity_penalty (0-10, higher = worse) + per-factor breakdown. Hard tags: ml/realtime/blockchain/hardware/compliance/custom-ai/regulated/on-device-ai/iot.
  • compute_collection_scoresCompute 12 deterministic collection scores (0-100) + badges + death reason for an enriched idea.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute 12 deterministic collection scores (0-100) + badges + death reason for an enriched idea. Pure math. No external calls.
  • compute_crossed_matrixCrossed-product audit explorer.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Crossed-product audit explorer. Same input as compute_dealbreakers_v2 — returns substrate verdict (no-observer baseline) + crossed verdict (when observer supplied) + a 5-row matrix of {solo, cofounded_technical, cofounded_business, domain_expert, serial} archetype verdicts. Never persists; meant for the dashboard "view as [archetype]" dropdown and for previewing a verdict before committing to it.
  • compute_dealbreakers_v2Methodology v2 dealbreakers — stage-aware weights + confidence-weighted lens scoring + risk-asymmetric verdict (GO requires score≥80 AND zero red flags AND avg confidence≥0.6).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Methodology v2 dealbreakers — stage-aware weights + confidence-weighted lens scoring + risk-asymmetric verdict (GO requires score≥80 AND zero red flags AND avg confidence≥0.6). Optional `observer` triggers the crossed-product pipeline: substrate verdict (no-observer baseline) PLUS crossed verdict (observer-perturbed weights, risk-tolerance shifted thresholds) PLUS 5-row archetype matrix. The KILL gate (≥2 blockers / score<50) is observer-invariant — fatal stays fatal.
  • compute_funding_momentumCompute funding_momentum_score (0-10) + badge (HOT/WARM/COOL/COLD) from tier-weighted funding-article hit counts.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute funding_momentum_score (0-10) + badge (HOT/WARM/COOL/COLD) from tier-weighted funding-article hit counts.
  • compute_hiring_demandCompute hiring_demand_score (0-10) from priority-weighted ATS site hit counts (use registries/hiring-sources for priorities).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute hiring_demand_score (0-10) from priority-weighted ATS site hit counts (use registries/hiring-sources for priorities).
  • compute_lrs_compositeCompose lrs_final_100 (0-100) + label (WEAK/EMERGING/GOOD/STRONG/ELITE) + leaderboard_eligible flag + sub-percent breakdown.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compose lrs_final_100 (0-100) + label (WEAK/EMERGING/GOOD/STRONG/ELITE) + leaderboard_eligible flag + sub-percent breakdown. Weights: sv 0.25, sp 0.30, barrier 0.25, monetization 0.20.
  • compute_lrs_composite_v2LRS composite v2 — 6 components (SV, Pain, Barrier, Monet, X-Signal, Budget-Proof).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    LRS composite v2 — 6 components (SV, Pain, Barrier, Monet, X-Signal, Budget-Proof). Default Python weights 0.18/0.22/0.18/0.14/0.18/0.10 sum=1.0. Returns BOTH weighted score and equal-weight baseline (per OECD Handbook + Greco 2018 — equal-weight is defensible default when no outcome calibration exists). buildComplexityPenalty 0-10 subtracted from score. sectorProfile (ai_native/creator/crypto) opt-in reshuffles SV→0.16, X→0.20. Labels: THE_ROAR (≥80) / PROMISING (≥60) / EXPERIMENTAL (≥40) / WEAK_SIGNAL (<40).
  • compute_monetizationCompute monetization_score (0-21) + label + has_pricing_anchors from pricing anchors + model tags + deal cycle hint.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute monetization_score (0-21) + label + has_pricing_anchors from pricing anchors + model tags + deal cycle hint.
  • compute_multi_source_tamMulti-source TAM consensus.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Multi-source TAM consensus. Pass 2-3 sources of market-size text. Optional `estimateYear` per source — when supplied, the result includes yearRange and a hasStaleData flag (true if the span exceeds 5 years). Outliers are dropped by modified Z-score over the median absolute deviation when n≥4. Returns the extracted dollar amounts + consensus median + an agreement score 0..1, where 1 means every source lands within 20% of the median.
  • compute_ppc_spend_signalWave 5 N.4 — compute ppc_spend_score (0-10) + label (STRONG/CONFIRMED/WEAK/ABSENT) + market_saturation from PPC traffic projection (avgCpcUsd, totalMonthlySpendUsd, optional compet…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Wave 5 N.4 — compute ppc_spend_score (0-10) + label (STRONG/CONFIRMED/WEAK/ABSENT) + market_saturation from PPC traffic projection (avgCpcUsd, totalMonthlySpendUsd, optional competitorBidders + competition). Feed numbers from dataforseo_ad_traffic.
  • compute_social_painCompute social_pain_score (0-30) + total mentions + dominant perspective (business/consumer/trend/mixed).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute social_pain_score (0-30) + total mentions + dominant perspective (business/consumer/trend/mixed).
  • compute_urgency_compositeCompose composite_urgency_score (0-10) + badge (LOW/MEDIUM/HIGH/VERY_HIGH/EXTREME) from 3 sub-scores: news, pain, hiring.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compose composite_urgency_score (0-10) + badge (LOW/MEDIUM/HIGH/VERY_HIGH/EXTREME) from 3 sub-scores: news, pain, hiring.
  • compute_x_signalCompute x_signal_score (0-20) + recency share + positivity rate from X/Twitter mention counts.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Compute x_signal_score (0-20) + recency share + positivity rate from X/Twitter mention counts.
Only reads 4Claude Code: allow
  • compute_search_velocityCompute search_velocity_score (0-25) from Trends timeline values + rising queries count + geo region count.No findings

    Why it is in this group

    • The name "compute_search_velocity" says "search": a word for reading.
    Description, as the server wrote it
    Compute search_velocity_score (0-25) from Trends timeline values + rising queries count + geo region count.
  • compute_search_velocity_v2Search velocity (0-25) v2 — canonical 0.40*volume + 0.30*trend + 0.20*intent + 0.10*geo.No findings

    Why it is in this group

    • The name "compute_search_velocity_v2" says "search": a word for reading.
    Description, as the server wrote it
    Search velocity (0-25) v2 — canonical 0.40*volume + 0.30*trend + 0.20*intent + 0.10*geo. CRITICAL: externalVolumeNorm MUST come from external sources (Amazon BSR / app store installs / job-board postings) — NOT the Trends timeline (would double-count, since Trends is itself normalized 0-100 within window). trendNorm is derived internally from trendsTimelineValues. Trends peak<50 zeroes the trend component (Yotpo SEO floor). Optional daysSinceLastSignal applies exponential freshness decay (search half-life 90d).
  • get_startedWhat this server is, what it will do for you right now without an account, and what an account adds.No findings

    Why it is in this group

    • The name "get_started" says "get": a word for reading.
    Description, as the server wrote it
    What this server is, what it will do for you right now without an account, and what an account adds. Call this first if you have no API key — it answers in one round trip instead of sending you to a website.
  • validate_unit_economicsSanity-check a unit-economics row before publishing it in a business-model slide.No findings

    Why it is in this group

    • The name "validate_unit_economics" says "validate": a word for reading.
    Description, as the server wrote it
    Sanity-check a unit-economics row before publishing it in a business-model slide. Catches the math-drift class of failures (customers × ARPU ≠ revenue), enforces the LTV/CAC ≥ 1.5 floor, the cohort-positivity check, and CAC payback bounds. Returns {ok, errors[{rule, severity, detail}], derived{ratios}}. Skills MUST regenerate the row when ok=false (block-severity errors); warn-severity errors should be surfaced in the final report but do not gate publication. No LLM calls.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ideaudit-tools https://api.inite.studio/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__ideaudit-tools__get_started",
      "mcp__ideaudit-tools__compute_search_velocity_v2",
      "mcp__ideaudit-tools__compute_search_velocity",
      "mcp__ideaudit-tools__validate_unit_economics"
    ],
    "ask": [
      "mcp__ideaudit-tools__compute_barrier",
      "mcp__ideaudit-tools__compute_budget_proof",
      "mcp__ideaudit-tools__compute_build_complexity",
      "mcp__ideaudit-tools__compute_collection_scores",
      "mcp__ideaudit-tools__compute_crossed_matrix",
      "mcp__ideaudit-tools__compute_dealbreakers_v2",
      "mcp__ideaudit-tools__compute_funding_momentum",
      "mcp__ideaudit-tools__compute_hiring_demand",
      "mcp__ideaudit-tools__compute_lrs_composite_v2",
      "mcp__ideaudit-tools__compute_lrs_composite",
      "mcp__ideaudit-tools__compute_monetization",
      "mcp__ideaudit-tools__compute_multi_source_tam",
      "mcp__ideaudit-tools__compute_ppc_spend_signal",
      "mcp__ideaudit-tools__compute_social_pain",
      "mcp__ideaudit-tools__compute_urgency_composite",
      "mcp__ideaudit-tools__compute_x_signal"
    ],
    "deny": [
      "mcp__ideaudit-tools__derive_kill_criteria"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as ideaudit-tools. Review it before you use it.