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
On their server. What you send to it goes to them.
What you need
Nothing: it answered without a login
Tools
10 tools
Its own safety labels
0 read-only, 10 with no label
Memory it takes
About 790 tokens of your AI's memory, just for its tool descriptions
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 the daily test on 13 Nov 2026.
Is ChinaTravelChina MCP server safe?
None of the hidden-instruction wordings we know were found in its 10 tool descriptions.
0 of its 10 tools are labeled read-only; the others may change or send things.
Overall it scored 77/100 on 13 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.
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
10 tools, in the server's own words.
search_destinations
Search published destination cities in the ChinaTravelChina catalog
get_destination_details
Get a published destination city with attractions and routes
search_attractions
Search published attractions
get_attraction_details
Get attraction details and nearby catalog places
compare_transport_routes
Compare catalog transport corridors between two cities.
find_nearby_attractions
Find published attractions near a latitude and longitude.
estimate_trip_budget
Illustrative budget in Chinese yuan.
generate_itinerary
Build a day-by-day plan from published cities and attractions.
get_travel_requirements
List travel-requirement orientation pages, or open one by name.
!Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described10 warnings
!search_destinations: Inputs with no description: query
!get_destination_details: Inputs with no description: slug
!search_attractions: Inputs with no description: query
!get_attraction_details: Inputs with no description: slug
!compare_transport_routes: Inputs with no description: originSlug, destinationSlug
!find_nearby_attractions: Inputs with no description: lat, lng, radiusKm
!estimate_trip_budget: Inputs with no description: citySlug, days, travelers, style
!generate_itinerary: Inputs with no description: citySlugs, days, interests, pace
and 2 more
note
!
Tools are labeled safe or dangerous1 warning
!10 of 10 tools have no safety label (read-only or dangerous): search_destinations, get_destination_details, search_attractions, get_attraction_details, compare_transport_routes, find_nearby_attractions, estimate_trip_budget, generate_itiner
note
!
Follows MCP best practices (not scored yet)2 tips (not scored)
!10 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): search_destinations, get_destination_details, search_attractions, get_attraction_details, compare_transport_routes, find_nearby_attractions and 4
!10 tools don't say whether they reach outside services like the web (openWorldHint): search_destinations, get_destination_details, search_attractions, get_attraction_details, compare_transport_routes, find_nearby_attractions and 4 more
note
✓
ConnectsConnected in 1.4 s
pass
✓
Lists its toolsFound 10 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 enoughAll good
✓Connecting took 1.4 s
✓Listing tools took 207 ms
pass
–
Tools work with good inputsNot tested
–search_destinations: Not run: no safety label (if you own this server, test again in owner mode)
–get_destination_details: Not run: no safety label (if you own this server, test again in owner mode)
–search_attractions: Not run: no safety label (if you own this server, test again in owner mode)
–get_attraction_details: Not run: no safety label (if you own this server, test again in owner mode)
–compare_transport_routes: Not run: no safety label (if you own this server, test again in owner mode)
–find_nearby_attractions: Not run: no safety label (if you own this server, test again in owner mode)
–estimate_trip_budget: Not run: no safety label (if you own this server, test again in owner mode)
–generate_itinerary: Not run: no safety label (if you own this server, test again in owner mode)
and 2 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
–
No known hidden instructions in tool answers (not scored yet)No tool answered, so there were no answers to read
not tested
Show this score on GitHub
Free for every server in the directory. Paste this into your README: the badge always shows the newest score, from the daily test, a test on our website or a Monitor test.