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
20 tools
Its own safety labels
18 read-only, 2 labeled as changing things
Memory it takes
About 4,400 tokens of your AI's memory, just for its tool descriptions
Largest answer
About 25.3 KB in our test
Tools that look alike
8 pairs of tools with nearly the same description, so the AI may pick the wrong one
Speed
Average answer in our test: 156 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 the daily test on 15 Nov 2026.
Is BitTuitive MCP server safe?
None of the hidden-instruction wordings we know were found in its 20 tool descriptions.
Its error messages showed no secrets or internal details.
18 of its 20 tools are labeled read-only; the others may change or send things.
Overall it scored 84/100 on 15 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.
!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 described13 warnings
!best_endpoint: Inputs with no description: limit
!scoreboard_search: Inputs with no description: data_type, protocol, min_score, limit, offset
!scoreboard_categories: Inputs with no description: top
!scoreboard_endpoint: Inputs with no description: id
!route_call: Inputs with no description: data_type
!get_weather_current and get_weather_forecast have nearly the same description (78% of their words are shared; the only difference: "current", "condition", "data" vs "forecast", "hourly", "plus"), so an AI may not know which to pick
!get_btc_oracle and get_btc_pro have nearly the same description (65% of their words are shared; the only difference: "btc", "price", "hash" vs "oracle", "100", "data"), so an AI may not know which to pick
!get_airport_delays and get_travel_airport have nearly the same description (65% of their words are shared; the only difference: "ground", "stop", "program" vs "required", "event", "plus"), so an AI may not know which to pick
and 5 more
note
!
Bad inputs give a clean error4 warnings
!best_endpoint: Accepted missing required input "need" without complaining
!best_endpoint: Accepted wrong type for "need" without complaining
!scoreboard_search: Accepted wrong type for "q" without complaining
!route_endpoints: Accepted wrong type for "data_type" without complaining
and 17 more
note
!
Follows MCP best practices (not scored yet)1 tip (not scored)
!1 tool not labeled read-only doesn't say whether running it twice is safe (idempotentHint): route_call
note
✓
ConnectsConnected in 582 ms
pass
✓
Lists its toolsFound 20 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
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
✓
Tools work with good inputsAll good
✓best_endpoint: Worked (234 ms)
✓scoreboard_search: Worked (210 ms)
✓scoreboard_categories: Worked (239 ms)
✓scoreboard_endpoint: Answered with an error, probably because of our sample input: { "error": { "detail": "service not found" } } {"error":{"detail":"service not found"}}
✓bittuitive_pricing: Worked (137 ms)
✓route_endpoints: Worked (150 ms)
✓get_btc_price: Answered with an error, probably because of our sample input: { "status": "payment_required", "error": "payment_required", "endpoint": "btc_price", "amount_sats": 10, "invoice": "lnbc100n1p4059wtpp5tqe…
✓get_btc_oracle: Answered with an error, probably because of our sample input: { "status": "payment_required", "error": "payment_required", "endpoint": "btc_oracle", "amount_sats": 50, "invoice": "lnbc500n1p4059wtpp5kk…
and 12 more
pass
✓
Tools work together4 chains working
✓best_endpoint → scoreboard_endpoint: scoreboard_endpoint found what best_endpoint returned (id = "67f923fdaebe")
✓scoreboard_search → scoreboard_endpoint: scoreboard_endpoint found what scoreboard_search returned (id = "8c089fbf094b")
✓scoreboard_categories → scoreboard_endpoint: scoreboard_endpoint found what scoreboard_categories returned (id = "e9a259d10e90")
✓route_endpoints → scoreboard_endpoint: scoreboard_endpoint found what route_endpoints returned (id = "24d3c884e58e")
No secrets leakedChecked 34 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 47 answers from 18 tools: none of the hidden-instruction wordings we know were found. New wordings can get past this check.
pass
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.