AI Apps That Work free tools

● Active

com.aiappsthatwork/tools

Real cost per AI result, LLM prices, switch costs, shutdown dates, A/B test sizes and judge checks.

Connect this server

One click to install, or copy the config below. Suits: Cursor · HTTP clients.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "tools": {
      "url": "https://aiappsthatwork.com/mcp"
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --transport http tools https://aiappsthatwork.com/mcp
VS Code
code --add-mcp '{"name":"tools","type":"http","url":"https://aiappsthatwork.com/mcp"}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Testing & QA
Version
1.0.1
Registry
active
Published
11/14/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: AI Apps That Work free tools is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit 8 days ago (Nov 14, 2026), 0 open issues.
Official registry
Active
Published as com.aiappsthatwork/tools in the official MCP registry, version 1.0.1.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
Hosted by the publisher
Your client talks to aiappsthatwork.com: prompts and tool arguments leave your machine for that host.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 05:07 UTCStatus history & uptime →
● Working152 msprotocol 2025-06-18v1.0.0tools

The endpoint answered the MCP handshake as "AI Apps That Work free tools" and listed 8 tools. Answering since Nov 18, 2026.

Context cost ≈ 8.3k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 8 tools.

Tools (8)

  • real_cost_per_result4 params

    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.

    Show parameters
    • stepsarrayrequiredThe AI steps behind one request, priced from /models.json. Their costs add up to the cost per request.
    • workedFirstTimePctnumberrequiredShare of results that worked first time: no try again, undo, fix, re-ask or overrule. 1 to 100.
    • requestsPerMonthnumberrequiredRequests per month, try-agains included
    • pricingobjectCredit pricing. Defaults: $10 for 1,000 credits, 1 credit per request, a 2.9% + $0.30 fee and a 70% target margin.
  • model_switch_cost2 params

    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.

    Show parameters
    • fromstringrequiredThe current model: an LLM id from /models.json (openai/gpt-4o), an OpenRouter id or the model's name
    • tostringrequiredThe new model: an LLM id from /models.json (openai/gpt-6-luna), an OpenRouter id or the model's name
  • model_prices3 params

    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.

    Show parameters
    • querystringA model id such as 'gpt-4o' (only exact id matches, if any), or words that must all appear in the id, name or provider, such as 'claude sonnet'. Omitted: every
    • kindstringllm for text models priced per token, image per image, video per second
    • limitintegerMost models to return
  • model_shutdowns3 params

    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.

    Show parameters
    • querystringA model id such as 'gpt-4o' (only exact id matches, if any), or words that must all appear in the model ids or provider, such as 'anthropic'. Omitted: every mod
    • includePastbooleanInclude shutdowns whose date has passed
    • todaystringDate to count days from, YYYY-MM-DD. Omitted: today in UTC.
  • ab_test_sample_size5 params

    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.

    Show parameters
    • baselinePctnumberrequiredShare of version A's (the current prompt or model) results that work first time, percent (above 0, below 100)
    • targetPctnumberrequiredShare of version B's results that work first time, percent (above 0, below 100)
    • confidencePctnumberConfidence level, percent. Two-sided.
    • powerPctnumberChance of detecting a real difference of this size, percent
    • resultsPerDaynumberResults per day across both versions, split evenly. Gives the number of days.
  • judge_agreement2 params

    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.

    Show parameters
    • rowsarrayOne row per result. Common words are mapped onto two verdicts: worked (worked, pass, yes, true, 1, good, kept, accepted, ok) and didn't work (didn't work, fail,
    • csvstringThe same data as CSV or TSV text instead of rows: columns named human and judge (and optionally note), or the first two columns in that order.
  • build_judge_prompt7 params

    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.

    Show parameters
    • blockstringrequiredWhat the AI step does. make: creates new content from a request (an image, a post, slides, advice); answer: replies to a question that has a right answer (a sup
    • featureDescriptionstringWho uses the feature, what they ask for and what a good result gives them
    • criteriaarrayPass conditions, one per item. Omitted: the starter conditions for the block.
    • workedExamplesarrayReal results that worked first time; labelled pass in the prompt
    • failedExamplesarrayReal results that didn't work; labelled fail in the prompt
    • outputFormatstringHow the judge answers
    • includeReasoningbooleanWhether the judge writes a short reason before its verdict
  • launch_checklist2 params

    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.

    Show parameters
    • donearrayIds of checks already done. Ids: spend-cap, rate-limits, server-keys, capped-retries, provider-budget, every-call-charged, deduct-server-side, refund-failures,
    • groupstringOnly checks in one group: cost (cost and abuse), charging (charging for ai use), traceability (a record of every ai result), signals (what worked, for whom, at

Checked by Serverdex with a plain initialize + tools/list call to aiappsthatwork.com/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 21, 2026
Stars
0
Forks
0
Last push
Nov 14, 2026
License
MIT

ai-costsclaude-codecursorevalsllmllm-as-a-judgellm-pricingmcpmcp-servermodel-context-protocol

From the README

AI Apps That Work: free MCP server for people building AI apps Your coding agent can look up what your AI features really cost and what to change: real cost per AI result, current LLM prices, model switch costs, model shutdown dates, A/B test sample sizes and LLM-judge checks. • Server URL: https://aiappsthatwork.com/mcp (Streamable HTTP) • Free, read-only, no sign-up and no API key • Official MCP registry: com.aiappsthatwork/tools • Docs: https://aiappsthatwork.com/connect • The same tools in a browser: https://aiappsthatwork.com/tools This repository holds the setup docs and client config files. The server itself runs at aiappsthatwork.com; its code is not in this repository. Connect Claude Code Add --scope user to have it in every project. Or copy .mcp.json into your project. Cursor: add this to ~/.cursor/mcp.json (every project) or .cursor/mcp.json (one project). The same file is in .cursor/mcp.json. VS Code: copy .vscode/mcp.json into your project. Claude on the web and desktop: add a custom connector with the URL https://aiappsthatwork.com/mcp and leave the advanced settings empty. ChatGPT: in developer mode, create an app with the URL https://aiappsthatwork.com/mcp and no authentication. Any other MCP client: use the URL above with the Streamable HTTP transport and no authentication. Tools Every tool is read-only and has a title. Every answer includes a link to a page on aiappsthatwork.com that shows the same result. Example prompts 1.…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://aiappsthatwork.com/mcp

The most-starred Testing & QA servers in the index, with their live-check result.

ServerStarsLast pushLive check
Keploy19,937Nov 2026Needs sign-in
e2e14,110Nov 2026Local / not checked
Mockserver5,011Nov 2026Local / not checked
Reticle1,326Nov 2026Local / not checked
Flutter Skill409Sep 2026Local / not checked

AI Apps That Work free tools: questions people ask

Is AI Apps That Work free tools a remote or a local MCP server?
According to its entry in the official MCP registry, AI Apps That Work free tools ships as a hosted endpoint (streamable-http) that your client connects to by URL.
Does AI Apps That Work free tools need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is AI Apps That Work free tools safe to use?
Looks healthy: AI Apps That Work free tools is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is AI Apps That Work free tools still maintained?
Active: the repository's last commit 8 days ago. Last push Nov 14, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
What tools does AI Apps That Work free tools expose?
8 tools as listed by the server itself during the live check, including real_cost_per_result, model_switch_cost, model_prices, model_shutdowns, ab_test_sample_size. The full list with parameters is in the Live check section above.
How do I add AI Apps That Work free tools to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
Browse all Testing & QA →

Add the badge to your site

Show visitors that AI Apps That Work free tools is listed here — it’s also the link we check for a free listing.

AI Apps That Work free tools — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/com-aiappsthatwork-tools?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="AI Apps That Work free tools — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![AI Apps That Work free tools — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/com-aiappsthatwork-tools?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/com-aiappsthatwork-tools) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/com-aiappsthatwork-tools) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/com-aiappsthatwork-tools)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/com-aiappsthatwork-tools"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/com-aiappsthatwork-tools"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/com-aiappsthatwork-tools"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).