QAmcp

Copied. Paste it into Claude Code, Cursor or Codex: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

SoonYour score can change any day. QAmcp Monitor tests your server every hour and emails you when it breaks.See what Monitor does →

Directory / Genexxis paid agent tools (x402)

Genexxis paid agent tools (x402)

Q: Is Genexxis paid agent tools (x402) MCP server safe?

QAmcp's test on 31 Oct 2026: No hidden instructions were found in its tool descriptions. 0 of its 60 tools are labeled read-only; the others may change or send things. Overall it scored 77/100 on 31 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.

by mcp.genexxis.com · https://mcp.genexxis.com/mcp

90 x402 tools: deal-doc red flags, token verdicts, sanctions, SEC data, safe-pay checks, DeFi

88 tools✓ no account neededPricing: not listed

Visit website

77 /100

PASS · WITH NOTES

Partial: 8 of 11 checks · 31 Oct 2026

Is Genexxis paid agent tools (x402) MCP server safe?

No hidden instructions were found in its tool descriptions.
0 of its 60 tools are labeled read-only; the others may change or send things.
Overall it scored 77/100 on 31 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

60 tools, in the server's own words.

list_services

Free.

airports_status

Disruption check for one airport: active FAA programs (ground stop, ground delay program, arrival/departure delays, closures) with reason and delay minutes, de…

airports_delays

All current FAA delay programs nationwide (ground stops, ground delay programs, airspace flow programs, arrival/departure delays, closures) sorted by severity,…

airports_weather

Decoded METAR and TAF (next 12 h) for up to 10 ICAO stations worldwide: wind, visibility, ceiling, flight category, temperature, weather, raw reports.

intel_find

Find the best x402 endpoints for a task.

intel_benchmark

Market benchmark for an x402 category: supply (endpoints, sellers), demand (30-day payers, calls, estimated revenue), price quartiles for all and proven seller…

intel_recommend

Which API should I call?

carry_ranking

Carry ranking of ~38 currencies vs a funding currency: policy-rate differential in pp (sorted desc), 1-year FX change vs the funder where official fixings exis…

carry_pair

Carry view of one currency pair: both policy rates with central bank and last change, differential in pp, which side earns the carry, current official FX rate …

carry_convert

Convert an amount between ~50 currencies at the official reference rate (Bank Al-Maghrib for MAD pairs, ECB otherwise, cross via EUR), with rate, date and sour…

chainread_read_contract

Call any view/pure function with a human-readable signature on Ethereum, Base, Arbitrum, Optimism, Polygon or BSC: decoded result, raw hex, block number, chain…

chainread_multicall

Up to 20 contract reads on one chain in a single Multicall3 request; each call returns success, decoded result and raw hex, or its revert reason.

chainread_resolve

ENS (Ethereum) and Basename (*.base.eth on Base) resolution: name to address with avatar, url, twitter, github, description records, or address to forward-veri…

chainread_token

Token metadata for any contract: ERC-20 name, symbol, decimals, total supply (raw and formatted), or ERC-721 / ERC-1155 detection via ERC-165 interfaces.

ciaudit_dockerfile

Lint a Dockerfile: base image pinning, root user, curl|sh, remote ADD, secrets in ENV/ARG, apt/pip/npm hygiene, chmod 777, EXPOSE 22, HEALTHCHECK, layer cache …

ciaudit_compose

Lint a docker-compose file: privileged, host network/pid/ipc, Docker socket mounts, SYS_ADMIN/ALL capabilities, unpinned images, database ports published on al…

ciaudit_github_actions

Lint a GitHub Actions workflow: actions not pinned to a commit SHA, missing or write-all permissions, pull_request_target with PR head checkout, script injecti…

cloudprice_gpu

Cheapest cloud GPU-hour for a GPU model (H100, H200, B200, A100, MI300X, L40S, L4, A10G, A10, V100, T4) across AWS and Azure regions, on-demand or spot, plus p…

cloudprice_instance

Hourly price of one cloud instance type in every region where it is sold (AWS EC2 or Azure VM SKU), on-demand and spot, cheapest region first.

cloudprice_compute

Cheapest AWS EC2 instances (Linux) with at least the given vCPU and memory, on-demand or spot, optionally in one region.

cryptonews_top

Top crypto stories of the last N hours, deduplicated across 13 outlets and ranked by number of distinct outlets reporting them, then recency: headline, outlets…

cryptonews_search

Crypto headlines of the last 72 h matching keywords or tickers (all words must match; tickers and asset names like ETH/ethereum map to tags), newest first, wit…

cve_cve

CVE lookup by id or NVD keyword search (severity, days, maxItems): CVSS v3.1/v4 score+vector, CWE, affected products, references, CISA KEV status, EPSS score a…

cve_kev

Latest CISA Known Exploited Vulnerabilities (filter by days, vendor, product, ransomware use) with due dates, required action and EPSS score joined.

and 36 more

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Ready for the newest MCP version
1 warning
- !Uses an older MCP version (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described
1 warning
- !domainaudit_domain_info and domainaudit_whois_bulk have nearly the same description (62% of their words are shared; the only difference: "dns", "code", "plus" vs "data", "looked", "parallel"), so an AI may not know which to pick
note
!
Tools are labeled safe or dangerous
1 warning
- !88 of 88 tools have no safety label (read-only or dangerous): list_services, airports_status, airports_delays, airports_weather, intel_find, intel_benchmark, intel_recommend, carry_ranking, carry_pair, carry_convert, chainread_read_contract
note
!
Follows MCP best practices (not scored yet)
3 tips (not scored)
- !88 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): list_services, airports_status, airports_delays, airports_weather, intel_find, intel_benchmark and 82 more
- !88 tools don't say whether they reach outside services like the web (openWorldHint): list_services, airports_status, airports_delays, airports_weather, intel_find, intel_benchmark and 82 more
- !The tool list is about 59 KB (roughly 15k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
note
✓
ConnectsConnected in 1.3 s
pass
✓
Lists its toolsFound 88 tools
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Fast enough
All good
- ✓Connecting took 1.3 s
- ✓Listing tools took 258 ms
pass
–
Tools work with good inputs
Not tested
- –list_services: Not run: no safety label (if you own this server, test again in owner mode)
- –airports_status: Not run: no safety label (if you own this server, test again in owner mode)
- –airports_delays: Not run: no safety label (if you own this server, test again in owner mode)
- –airports_weather: Not run: no safety label (if you own this server, test again in owner mode)
- –intel_find: Not run: no safety label (if you own this server, test again in owner mode)
- –intel_benchmark: Not run: no safety label (if you own this server, test again in owner mode)
- –intel_recommend: Not run: no safety label (if you own this server, test again in owner mode)
- –carry_ranking: Not run: no safety label (if you own this server, test again in owner mode)
- and 32 more
not tested
–
Bad inputs give a clean errorNot tested
not 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 check
not tested

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://mcp.genexxis.com/mcp

Show 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.

[![QAmcp score](https://qamcp.dev/s/com-genexxis-data-apis.svg)](https://qamcp.dev/s/com-genexxis-data-apis.html)

Score over time

31 Oct 202677

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Genexxis paid agent tools (x402), signed in with GitHub, one per person. Reviews never change the score.

Is this your server? Get an alert the moment it breaks.

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