AI Apps That Work free tools
Free MCP tools for LLM prices, switch costs, shutdown dates and A/B test sizes
Answered our latest tool-list check 16 hours ago with 8 tools. It will be marked verified after 3 successful checks in 7 days.
- Pricing
- Free
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 1.0.1
- Listing updated
- 3 days ago
About AI Apps That Work free tools
AI Apps That Work free tools is a free MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
Cost per result that worked, rather than cost per request, is the idea behind the headline tool. real_cost_per_result prices the AI steps in one request from current list prices, divides by the share that works first time, and reports monthly wasted spend plus credit-pricing margin numbers.
The others compare and check: model_switch_cost sets two models side by side on six task shapes such as invoice extraction and lead scoring and gives a break-even first-time-success rate; model_prices and model_shutdowns return list prices and announced API shutdown dates with source pages and check dates; ab_test_sample_size gives the sample each prompt version needs; judge_agreement scores an LLM judge against human verdicts with Cohen's kappa; build_judge_prompt writes a pass/fail judge prompt; launch_checklist lists pre-launch checks.
All eight tools are read-only and need no key or sign-up. Text-model prices are re-checked daily against OpenRouter and LiteLLM, and inputs are computed in memory and discarded.
Install
Run in a terminal
claude mcp add --transport http tools https://aiappsthatwork.com/mcpAdd to Settings → Connectors → Add custom connector
https://aiappsthatwork.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"tools": {
"url": "https://aiappsthatwork.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"tools": {
"type": "http",
"url": "https://aiappsthatwork.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"tools": {
"serverUrl": "https://aiappsthatwork.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"tools": {
"type": "http",
"url": "https://aiappsthatwork.com/mcp"
}
}
}Tools this server provides (8)
Read directly from the server.
- real_cost_per_result
- 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 bre
- model_switch_cost
- 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 sh
- model_prices
- 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.
- model_shutdowns
- 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.
- ab_test_sample_size
- 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.
- judge_agreement
- 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
- build_judge_prompt
- 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.
- launch_checklist
- 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.
What it does
- Real cost per result
- Turns request cost into cost per result that worked first time, plus wasted spend.
- Model switch comparison
- Compares two models on six task shapes with a break-even point.
- Prices and shutdowns
- List prices with check dates and announced API shutdown dates.
- A/B sample sizing
- Results needed per prompt or model version at a daily volume.
- Judge checks
- Agreement, kappa and a trust verdict for an LLM judge.
- Launch checklist
- AI-specific pre-launch checks with a request for a coding agent.
Good for
- Estimate what each working AI answer costs
- Decide whether to move to a cheaper model
- Find which models are being retired soon
- Size a prompt A/B test
- Check whether an LLM judge can be trusted
Pricing
Free
Prices change. Check aiappsthatwork.com before you buy.
AI Apps That Work free tools FAQ
Does it need a key?
No. It is free, read-only and needs no sign-up or API key.
How fresh are the prices?
Text-model prices are re-checked daily against OpenRouter and LiteLLM, and each carries its check date.
Is my input stored?
The README says inputs are computed in memory and thrown away; only agent kind, client version, tool name, outcome and duration are recorded.
What does the trust verdict require?
Kappa of 0.6 or more with at least 80% recall on every verdict; under 30 results is too few.
Is AI Apps That Work free tools free?
Yes. AI Apps That Work free tools is free to use.
How do I add AI Apps That Work free tools to Claude Code?
Run this command in your terminal: claude mcp add --transport http tools https://aiappsthatwork.com/mcp
What are the best alternatives to AI Apps That Work free tools?
The closest alternatives to AI Apps That Work free tools are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to AI Apps That Work free tools

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools