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 / GadgetHumans - Token Safety & Agent Tools API

GadgetHumans - Token Safety & Agent Tools API

Q: Is GadgetHumans - Token Safety & Agent Tools API MCP server safe?

QAmcp's test on 2 Nov 2026: None of the hidden-instruction wordings we know were found in its tool descriptions. 0 of its 49 tools are labeled read-only; the others may change or send things. Overall it scored 77/100 on 2 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.

by api.gadgethumans.com · https://api.gadgethumans.com/mcp

Honeypot, rug-pull & sell-tax check for Base tokens, $0.01/call via x402; 49 agent tools.

49 tools✓ no account neededPricing: not listed

Visit website

77 /100

PASS · WITH NOTES

Partial: 8 of 11 checks · 2 Nov 2026

Is GadgetHumans - Token Safety & Agent Tools API MCP server safe?

None of the hidden-instruction wordings we know were found in its tool descriptions.
0 of its 49 tools are labeled read-only; the others may change or send things.
Overall it scored 77/100 on 2 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 it can do

49 tools, in the server's own words.

token_verdict

Pre-trade risk verdict on a Base token, $0.01.

prediction_odds

Prediction-market odds and implied probability, $0.01.

prediction_scan

Live prediction-market board scan, $0.25.

affiliate_search

Search Amazon products and get affiliate links.

agent_memory

VAULT: Persistent agent memory — the KEY tool.

agent_profile

VAULT: View your agent profile — see your agent ID, total stored data items, usage stats, and subscription status.

memory_search

VAULT SEARCH: Search across ALL your stored memories by keyword.

memory_list

VAULT LIST: List all memory keys in your vault.

get_weather

Current weather for any city

get_forecast

7-day weather forecast for any city

get_crypto_prices

Get real-time cryptocurrency prices from Binance

convert_currency

Convert between currencies using real-time rates

geocode

Forward geocode an address to coordinates

dns_lookup

Look up DNS records for any domain

geolocate_ip

Get geolocation data for any IP address

get_air_quality

Get current air quality data for any city (AQI, PM2.5, PM10)

search_web

Search the web using DuckDuckGo

parse_rss_feed

Parse RSS/Atom feed to JSON

check_ssl_certificate

Check SSL certificate for a domain

decode_jwt

Decode a JWT token into header, payload, signature

check_password_strength

Check password strength with score and crack time estimate

detect_language

Detect the language of provided text with confidence score

generate_qr_code

Generate QR code as base64 PNG image

generate_password

Generate secure random passwords

and 25 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 (2024-11-05). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described
21 warnings
- !search_web: Inputs with no description: query
- !parse_rss_feed: Inputs with no description: url
- !check_ssl_certificate: Inputs with no description: domain
- !decode_jwt: Inputs with no description: token
- !check_password_strength: Inputs with no description: password
- !detect_language: Inputs with no description: text
- !generate_password: Inputs with no description: numbers, symbols
- !hash_text: Inputs with no description: text
- and 13 more
note
!
Tools are labeled safe or dangerous
1 warning
- !49 of 49 tools have no safety label (read-only or dangerous): token_verdict, prediction_odds, prediction_scan, affiliate_search, agent_memory, agent_profile, memory_search, memory_list, get_weather, get_forecast, get_crypto_prices, convert_
note
!
Follows MCP best practices (not scored yet)
2 tips (not scored)
- !49 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): token_verdict, prediction_odds, prediction_scan, affiliate_search, agent_memory, agent_profile and 43 more
- !49 tools don't say whether they reach outside services like the web (openWorldHint): token_verdict, prediction_odds, prediction_scan, affiliate_search, agent_memory, agent_profile and 43 more
note
✓
ConnectsConnected in 222 ms
pass
✓
Lists its toolsFound 49 tools
pass
✓
No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.
pass
✓
Fast enough
All good
- ✓Connecting took 222 ms
- ✓Listing tools took 33 ms
pass
–
Tools work with good inputs
Not tested
- –token_verdict: Not run: no safety label (if you own this server, test again in owner mode)
- –prediction_odds: Not run: no safety label (if you own this server, test again in owner mode)
- –prediction_scan: Not run: no safety label (if you own this server, test again in owner mode)
- –affiliate_search: Not run: no safety label (if you own this server, test again in owner mode)
- –agent_memory: Not run: no safety label (if you own this server, test again in owner mode)
- –agent_profile: Not run: no safety label (if you own this server, test again in owner mode)
- –memory_search: Not run: no safety label (if you own this server, test again in owner mode)
- –memory_list: 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://api.gadgethumans.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-gadgethumans-api-hub.svg)](https://qamcp.dev/s/com-gadgethumans-api-hub.html)

Score over time

2 Nov 202677

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use GadgetHumans - Token Safety & Agent Tools API, 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