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
4 tools
Its own safety labels
3 read-only, 1 labeled as changing things
Memory it takes
About 750 tokens of your AI's memory, just for its tool descriptions
Speed
Average answer in our test: 35 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 13 Nov 2026.
Is x-toolkit MCP server safe?
None of the hidden-instruction wordings we know were found in its 4 tool descriptions.
Its error messages showed no secrets or internal details.
3 of its 4 tools are labeled read-only; the others may change or send things.
Overall it scored 95/100 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
4 tools, in the server's own words.
read_x_articleread-only
Returns an X (Twitter) Article as Markdown with images in place.
get_x_video_transcriptread-only
Returns the transcript of the video in an X (Twitter) post: X's own captions when they exist, or a transcript x-toolkit made earlier.
transcribe_x_video
Transcribes the video in an X post that has no captions, one part (about 108 seconds of audio) per call.
read_x_postread-only
Returns a single X (Twitter) post as Markdown: author, date, text, the quoted post, image links and counts.
!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
✓
ConnectsConnected in 607 ms
pass
✓
Lists its toolsFound 4 tools
pass
✓
Every tool is describedAll 4 tools and their inputs are described
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
✓read_x_article: Answered with an error, probably because of our sample input: That doesn’t look like a link to a post on X. Pass one like https://x.com/name/status/123…
✓get_x_video_transcript: Answered with an error, probably because of our sample input: That doesn’t look like a link to a post on X. Pass one like https://x.com/name/status/123…
✓read_x_post: Answered with an error, probably because of our sample input: That doesn’t look like a link to a post on X. Pass one like https://x.com/name/status/123…
–transcribe_x_video: Not run: labeled as changing data
pass
✓
Bad inputs give a clean errorAll good
✓read_x_article: Refused missing required input "url" with a clear error
✓read_x_article: Refused wrong type for "url" with a clear error
✓get_x_video_transcript: Refused missing required input "url" with a clear error
✓get_x_video_transcript: Refused wrong type for "url" with a clear error
✓read_x_post: Refused missing required input "url" with a clear error
✓read_x_post: Refused wrong type for "url" with a clear error
No secrets leakedChecked 9 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 9 answers from 3 tools: none of the hidden-instruction wordings we know were found. New wordings can get past this check.
pass
✓
Follows MCP best practices (not scored yet)Tool names, safety labels and tool list size follow the MCP guide
pass
–
Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
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.