# amit-timalsina/aiappsthatwork-mcp

Source: https://glimind.com/server/github%2Famit-timalsina%2Faiappsthatwork-mcp
Registry id: `github/amit-timalsina/aiappsthatwork-mcp`
Status: unknown

## Tools (8)

- `ab_test_sample_size`: Results needed per version and days at a given volume
- `build_judge_prompt`: A pass/fail judge prompt for one kind of AI step
- `judge_agreement`: Agreement rate, Cohen's kappa, per-verdict precision and recall, whether to trust the judge
- `launch_checklist`: AI-specific checks still to do before launch plus a request for a coding agent
- `model_prices`: List prices, context size, price source, and dates each price was checked and last changed
- `model_shutdowns`: Announced API shutdowns with replacement and source
- `model_switch_cost`: List prices of both models, cost per 1,000 requests on six common tasks, break-even point, shutdown date
- `real_cost_per_result`: Cost per request, real cost per result that worked, monthly wasted spend, credit pricing

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
