# ideaudit > ideaudit, an MCP server by inite.studio, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. The scoring behind an audit allowed to say no. Twenty deterministic tools, offline, no account. - Canonical: https://www.anchorterminal.com/tools/inite-ideaudit-tools - Markdown: https://www.anchorterminal.com/tools/inite-ideaudit-tools.md (~1,950 tokens) - Slim: https://www.anchorterminal.com/tools/inite-ideaudit-tools.min.md (~1,880 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/inite-ideaudit-tools.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-05 # ideaudit > Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/ - Kind: MCP server, by inite.studio (https://inite.studio) - Listed because: It's published in the registry under inite.studio, a namespace the registry only gives to whoever proves they control that domain. - What the official MCP registry says: The scoring behind an audit allowed to say no. Twenty deterministic tools, offline, no account. ## Facts - MCP registry: `studio.inite/ideaudit-tools` 1.1.0 - Endpoint: https://api.inite.studio/mcp (streamable HTTP) - Package: npm `@inite/ideaudit-tools` (stdio) - Source: https://github.com/inite-ai/ideaudit-mcp - Website: https://inite.studio - npm downloads a week: 35 - GitHub stars: 0 - Registry entry updated: 2026-09-07 ## Tools - Tools it lists (21, about 4,112 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-10-04 22:25 UTC): - `get_started`: 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… - `compute_barrier`: Compute barrier_score (0-24) + label (PRISTINE/OPEN/COMPETITIVE/CROWDED) from competitor counts + SERP noise fraction. - `compute_budget_proof`: Compute budget_proof_score (0-10) + label (STRONG/CONFIRMED/WEAK/ABSENT) + purchase_intent_pct from pricing hits + review-site hits + intent mentions. - `compute_build_complexity`: Compute build_complexity_penalty (0-10, higher = worse) + per-factor breakdown. Hard tags:… - `compute_collection_scores`: Compute 12 deterministic collection scores (0-100) + badges + death reason for an enriched idea. Pure math. No external calls. - `compute_crossed_matrix`: Crossed-product audit explorer. Same input as compute_dealbreakers_v2 — returns substrate verdict (no-observer baseline) + crossed verdict (when observer… - `compute_dealbreakers_v2`: Methodology v2 dealbreakers — stage-aware weights + confidence-weighted lens scoring + risk-asymmetric verdict (GO requires score≥80 AND zero red flags AND avg… - `compute_funding_momentum`: Compute funding_momentum_score (0-10) + badge (HOT/WARM/COOL/COLD) from tier-weighted funding-article hit counts. - `compute_hiring_demand`: Compute hiring_demand_score (0-10) from priority-weighted ATS site hit counts (use registries/hiring-sources for priorities). - `compute_lrs_composite_v2`: 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… - `compute_lrs_composite`: 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… - `compute_monetization`: Compute monetization_score (0-21) + label + has_pricing_anchors from pricing anchors + model tags + deal cycle hint. - `compute_multi_source_tam`: Multi-source TAM consensus. Pass 2-3 sources of market-size text. Optional `estimateYear` per source — when supplied, the result includes yearRange and a… - `compute_ppc_spend_signal`: Wave 5 N.4 — compute ppc_spend_score (0-10) + label (STRONG/CONFIRMED/WEAK/ABSENT) + market_saturation from PPC traffic projection (avgCpcUsd,… - `compute_search_velocity_v2`: 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… - `compute_search_velocity`: Compute search_velocity_score (0-25) from Trends timeline values + rising queries count + geo region count. - `compute_social_pain`: Compute social_pain_score (0-30) + total mentions + dominant perspective (business/consumer/trend/mixed). - `compute_urgency_composite`: Compose composite_urgency_score (0-10) + badge (LOW/MEDIUM/HIGH/VERY_HIGH/EXTREME) from 3 sub-scores: news, pain, hiring. - `compute_x_signal`: Compute x_signal_score (0-20) + recency share + positivity rate from X/Twitter mention counts. - `derive_kill_criteria`: 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… - `validate_unit_economics`: Sanity-check a unit-economics row before publishing it in a business-model slide. Catches the math-drift class of failures (customers × ARPU ≠ revenue),… - How its tools read to an agent (0 errors, 42 warnings, 1 note, about 4,112 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score): - warn TC11 compute_barrier: none of its 3 parameters has a description - warn TC11 compute_budget_proof: none of its 4 parameters has a description - warn TC11 compute_build_complexity: none of its 3 parameters has a description - warn TC11 compute_collection_scores: 1 parameter without a description: analysisId - warn TC11 compute_crossed_matrix: none of its 7 parameters has a description - warn TC11 compute_dealbreakers_v2: none of its 7 parameters has a description - warn TC11 compute_funding_momentum: none of its 2 parameters has a description - warn TC11 compute_hiring_demand: 4 parameters without a description: sites, sites[].domain, sites[].hits, sites[].priority - warn TC11 compute_lrs_composite: none of its 4 parameters has a description - warn TC11 compute_lrs_composite_v2: 7 parameters without a description: barrierScore, budgetProofScore, buildComplexityPenalty, monetizationScore, searchVelocityScore, socialPainScore and 1 more - warn TC11 compute_monetization: 1 parameter without a description: pricingAnchorsCount - warn TC11 compute_multi_source_tam: 3 parameters without a description: inputs, inputs[].source, inputs[].text - warn TC11 compute_ppc_spend_signal: none of its 4 parameters has a description - warn TC11 compute_search_velocity: 2 parameters without a description: geoRegionCount, risingQueriesCount - warn TC11 compute_social_pain: none of its 4 parameters has a description - warn TC11 compute_urgency_composite: none of its 3 parameters has a description - warn TC11 compute_x_signal: none of its 5 parameters has a description - warn TC11 derive_kill_criteria: 1 parameter without a description: icpDriftCount - warn TC11 validate_unit_economics: none of its 7 parameters has a description - warn TC13 compute_collection_scores: enrichedData (object with no properties) - warn TC13 derive_kill_criteria: dealbreakers (object with no properties), unitEcon (object with no properties) - warn TC16 compute_barrier: no readOnlyHint or destructiveHint - warn TC16 compute_budget_proof: no readOnlyHint or destructiveHint - warn TC16 compute_build_complexity: no readOnlyHint or destructiveHint - JSON: https://www.anchorterminal.com/api/v1/tools/inite-ideaudit-tools.json - Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming