Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / AI Rate Card
AI Rate Card
by airatecard.com · https://airatecard.com/mcp
Daily-checked AI model API prices from 120+ providers: search, compare, cheapest, cost estimates.
12 of 12 checks · 5 Nov 2026
At a glance
- Runs where
- On their server. What you send to it goes to them.
- What you need
- Nothing: it answered without a login
- Tools
- 13 tools
- Its own safety labels
- 13 read-only
- Memory it takes
- About 3,200 tokens of your AI's memory, just for its tool descriptions
- Largest answer
- About 33.1 KB in our test
- Speed
- Average answer in our test: 250 ms
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 5 Nov 2026.
Is AI Rate Card MCP server safe?
- None of the hidden-instruction wordings we know were found in its 13 tool descriptions.
- Its error messages showed no secrets or internal details.
- All 13 of its tools are labeled read-only.
- Overall it scored 70/100 on 5 Nov 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What this test does not check
- Its source code and packages.
- What a tool quietly does behind the scenes, such as writing a file or calling another service.
- Instructions hidden inside live tool answers. We only look for those in tool descriptions.
- Hidden instructions worded in a way our list doesn't know yet.
- Tools that could change something. Those are read, never run.
What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection
Known security advisories
It lists no public code, so there is nothing to look up in GitHub Security Advisories or OSV.dev. QAmcp tests how a server behaves. It does not scan source code.
What it can do
13 tools, in the server's own words.
search_offersread-onlySearch current AI model offers (one model at one provider = one offer) by words, model type and limits; priced offers first, doubtful prices after sane ones.
get_model_pricesread-onlyEvery seller's current price of one model (an id, or a name to search for), cheapest input first.
cheapest_offersread-onlyThe cheapest current offers (rows: one model at one provider) of one model type, by input price.
compare_modelsread-only2 to 5 models side by side: the best current offer of each and, for up to 4, every field compared (lowest and median input/output price, context, max output, p…
estimate_costread-onlyThe cost of a workload (input, output and cached input tokens, number of requests) at every current provider of one model, cheapest first, in USD - what the sa…
get_cardread-onlyOne card with its citation.
validate_provider_filesread-onlyFor a provider (seller) joining the catalog: check a models.yaml before putting it online - the same check as the wizard and POST /v1/provider/validate.
cheapest_for_workloadread-onlyThe cheapest offers for a whole monthly workload, ranked by monthly cost in USD: give a preset (a typical job; see list_workload_presets) and/or your own token…
list_workload_presetsread-onlyThe ready-made workloads of cheapest_for_workload: name, what job it is, tokens a month, context needed, model type.
list_articlesread-onlyAI Rate Card's articles on AI model prices (the cheapest models by task, price moves, costs), newest first, with their links - to quote or point a reader to.
cheapest_models_by_taskread-onlyThe n cheapest MODELS for a job (task): each model counted once at its own lowest current price (input tokens by default).
most_expensive_models_by_taskread-onlyThe n most expensive MODELS for a job (task): each model counted once at its own lowest current price, highest first - the top of the market.
median_price_by_taskread-onlyThe typical (median) current price of a job (task) across models, and the n models closest to it - what a normal price for this job is.
Test results
Safe mode: only tools labeled read-only were run. How the test works
- ✕Bad inputs give a clean errorfail
1 failed, 1 warning
- ✕search_offers: Crashed on wrong type for "query"
- !list_articles: Accepted wrong type for "lang" without complaining
- and 18 more
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Follows MCP best practices (not scored yet)note
1 tip (not scored)
- !13 tools don't say whether they reach outside services like the web (openWorldHint): search_offers, get_model_prices, cheapest_offers, compare_models, estimate_cost, get_card and 7 more
- !Resources and prompts worknote
2 warnings (3 prompts)
- !where_is_model_cheapest: Doesn't complain when the required input model is missing.
- !compare_models: Doesn't complain when the required input models is missing.
- and 1 more
- ✓ConnectsConnected in 1.2 spass
- ✓Lists its toolsFound 13 toolspass
- ✓Every tool is describedAll 13 tools and their inputs are describedpass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Tools work with good inputspass
All good
- ✓search_offers: Worked (270 ms)
- ✓get_model_prices: Worked (275 ms)
- ✓cheapest_offers: Worked (247 ms)
- ✓compare_models: Answered with an error, probably because of our sample input: models must be a list of 2 to 5 non-empty ids or names
- ✓estimate_cost: Worked (220 ms)
- ✓get_card: Answered with an error, probably because of our sample input: unknown card 'test' - card_id is offer:<offer_id>, model:<model_id> or seller:<provider_id>, ids as in search_offers rows
- ✓validate_provider_files: Worked (259 ms)
- ✓cheapest_for_workload: Answered with an error, probably because of our sample input: give a preset or input_tokens / output_tokens (tokens a month)
- and 5 more
- ✓Fast enoughpass
All good
- ✓Connecting took 1.2 s
- ✓Listing tools took 245 ms
- ✓Average tool answer: 250 ms
- ✓list_workload_presets: Slowest tool: list_workload_presets (305 ms)
- ✓No secrets leakedChecked 22 error messages: no secrets or internal detailspass
- –Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)not tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://airatecard.com/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/com-airatecard-ai-rate-card.html)Score over time
- 5 Nov 202670
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use AI Rate Card, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works