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 / InferCPI
InferCPI
by infercpi.com · https://infercpi.com/mcp
AI inference price index: token prices, cost per capability, open vs closed, hosts, cost per task.
Partial: 8 of 11 checks · 29 Oct 2026
Is InferCPI MCP server safe?
- No hidden instructions were found in its tool descriptions.
- 0 of its 10 tools are labeled read-only; the others may change or send things.
- Overall it scored 77/100 on 29 Oct 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 it can do
10 tools, in the server's own words.
index_latestLatest value of every index series (list-price chained/composition/hedonic, usage-weighted paid price, Törnqvist, OpenRouter shares, TPI replica) with dates, t…
index_seriesFull weekly history of one series as [[unix_ts, value], ...] plus its method string.
index_catalogueEvery series the index publishes: signal/key, point count, first and last date, method string.
basketEvery model priced in this week's list-price index: provider, blended $/1M (0.75 in + 0.25 out), Epoch capability score where matched.
eventsPriced events in first-party price lists, newest first: launch, price_cut, price_increase, removed, each with key, provider, old/new blended $/1M and pct.
speedLatest daily speed run, measured by the index: per model and route (openrouter default routing, openrouter_pinned to the first-party host, anthropic and openai…
model_priceBlended list $/1M for one model by any common name ('Claude Opus 5.5', 'anthropic/claude-opus-5.5', 'gpt-5.5'); matches by the index's name normaliser and retu…
open_vs_closedCheapest blended $/1M at each capability level (Epoch ECI 130/145/160) for closed models, open models at their lab's price and open models at the cheapest thir…
self_hostingWhat it costs per 1M tokens to leave the APIs: desk boxes (Mac Studio lease, RTX 5090 bought) at full and 25% duty, H100 rented by source (Vast, AWS, RunPod, C…
cost_per_taskMonthly measurement: dollars and tokens per completed task for the most-used models (fixed 8-task suite via OpenRouter at default settings, charged cost), reas…
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !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.
- !Every tool is describednote
3 warnings
- !index_series: Inputs with no description: signal, key, since
- !events: Inputs with no description: since, kind
- !model_price: Inputs with no description: name
- !Tools are labeled safe or dangerousnote
1 warning
- !10 of 10 tools have no safety label (read-only or dangerous): index_latest, index_series, index_catalogue, basket, events, speed, model_price, open_vs_closed, self_hosting, cost_per_task
- !Follows MCP best practices (not scored yet)note
2 tips (not scored)
- !10 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): index_latest, index_series, index_catalogue, basket, events, speed and 4 more
- !10 tools don't say whether they reach outside services like the web (openWorldHint): index_latest, index_series, index_catalogue, basket, events, speed and 4 more
- ✓ConnectsConnected in 687 mspass
- ✓Lists its toolsFound 10 toolspass
- ✓No hidden instructionsNo hidden instructions found in tool descriptionspass
- ✓Fast enoughpass
All good
- ✓Connecting took 687 ms
- ✓Listing tools took 96 ms
- –Tools work with good inputsnot tested
Not tested
- –index_latest: Not run: no safety label (if you own this server, test again in owner mode)
- –index_series: Not run: no safety label (if you own this server, test again in owner mode)
- –index_catalogue: Not run: no safety label (if you own this server, test again in owner mode)
- –basket: Not run: no safety label (if you own this server, test again in owner mode)
- –events: Not run: no safety label (if you own this server, test again in owner mode)
- –speed: Not run: no safety label (if you own this server, test again in owner mode)
- –model_price: Not run: no safety label (if you own this server, test again in owner mode)
- –open_vs_closed: Not run: no safety label (if you own this server, test again in owner mode)
- and 2 more
- –Bad inputs give a clean errorNot testednot tested
- –Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)not tested
- –No secrets leakedNo error messages to checknot tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://infercpi.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-infercpi-api.html)Score over time
- 29 Oct 202677
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use InferCPI, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works