Real cost per AI result, LLM prices, switch costs, shutdown dates, A/B test sizes and judge checks.
Scored across 8 tools
Each tool has a distinct role: statistical planning (ab_test_sample_size), judge construction (build_judge_prompt), judge validation (judge_agreement), launch readiness (launch_checklist), and three different cost operations (list lookup, two-model comparison, per-request/per-result pricing). The cost cluster—model_prices, model_switch_cost, real_cost_per_result—could be momentarily confused, but the descriptions clearly separate lookup, comparison, and per-result math.
All names are snake_case and readable, with no style mixing. Most are noun phrases describing the output (model_prices, launch_checklist, real_cost_per_result) while one uses verb_noun (build_judge_prompt), so the pattern is descriptive rather than a strict verb_noun convention.
Eight tools is well within the ideal range and each maps to a concrete deliverable (a sample size, a prompt, a kappa, a checklist, a price table, shutdown dates, a cost comparison, a per-result cost). No tool feels redundant or like padding.
The surface covers the advertised lifecycle: build a judge, validate it, size an experiment, price models, compare switching, compute real cost per result, and check launch readiness. Minor gaps remain—no tool to ingest raw result data and compute the worked-first-time share or pass rate, and no way to actually run/evaluate results—but an agent can work around these by doing the arithmetic itself.
Returns how many results each version of a prompt or model needs before a difference in how often results work first time is statistically real (two-proportion z-test, two-sided), the total across both versions, and how many days that takes at a given daily volume.
Inputs: targetPct (required), baselinePct (required), powerPct, confidencePct, +1 more. Returns: days, alpha, power, total, +7 more
Builds a pass/fail LLM-as-a-judge prompt for one kind of AI step (make, answer, transform, extract, judge, find, predict, plan, act or learn). Returns the prompt with {{input}} and {{result}} placeholders, numbered pass conditions (the block's starter conditions unless you send your own), up to 3 pass and 3 fail examples interleaved, and a JSON or XML answer format.
Inputs: block (required), criteria, outputFormat, failedExamples, +3 more. Returns: block, prompt, summary, criteria, +4 more
Compares a person's verdicts with an AI judge's verdicts on the same results. Returns the agreement rate, Cohen's kappa with confidence intervals, precision and recall per verdict, the agreement of a judge that always gives the most common verdict, a trust verdict (kappa 0.6 or more with at least 80% recall on every verdict; 0.4 to 0.6 is borderline; under 30 results is too few) and the rows where the two disagree.
Inputs: csv, rows. Returns: n, kappa, matrix, kappaCi, +12 more
The 20 AI-specific launch checks for an AI app (spending caps, rate limits, server-side keys, credit charging, version tags, records of which results worked first time, real cost per result, switching models safely). Returns the checks not yet done, each with why it matters and a request for a coding agent, plus one combined request.
Inputs: done, group. Returns: total, groups, summary, doneCount, +4 more
Looks up list prices for LLMs (USD per million input, output and cached input tokens, and context size), image models (USD per image by quality and size) and video models (USD per second by resolution), with each price's source page, the date prices were checked and any announced API shutdown.
Inputs: kind, limit, query. Returns: models, permalink, totalMatches, pricesChecked
Lists announced API shutdown dates for AI models from OpenAI, Anthropic, Google and other providers, with days left, the suggested replacement, the source page, and links to a cost comparison and a side-by-side test of the replacement where this site has them.
Inputs: query, today, includePast. Returns: count, today, permalink, shutdowns, +1 more
Compares two priced LLMs on six common task shapes (support answer, invoice extraction, lead scoring, email draft, translation, search re-ranking). Returns list prices, cost per 1,000 requests on each model, the cost ratio, the break-even (how often the new model's results must work first time, relative to the current one, to cost no more per result that works) and the current model's announced shutdown.
Inputs: to (required), from (required). Returns: to, from, note, tasks, +7 more
Prices the AI steps behind one request from current list prices (LLM tokens, images, video seconds or a fixed amount) and returns the cost per request, the real cost per result that worked first time (cost per request divided by the worked-first-time share), the monthly spend wasted on results that didn't work, and credit-pricing numbers: margin per result and the credits per request needed to break even or reach a target margin.
Inputs: steps (required), requestsPerMonth (required), workedFirstTimePct (required), pricing. Returns: steps, credits, summary, permalink, +6 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
LLM prices, cost estimates and break-even, plus your app's AI cost and margin per user.
AI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.
Daily LLM API prices, cost estimates and automation ROI tools from shurco.ai
LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.
Add one secure layer between your agents and this server.