AI Certificates MCP server
study.aicertificates/practice-examsaicertificates.studystreamable-httpv1.0.0Scanned
Practice questions for the four Claude certifications. The assistant never sees the key.
5 tools: 3 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the AI Certificates MCP server can do
The AI Certificates MCP server is published by aicertificates.study, a domain the MCP Registry verified. It has 5 tools. It can create or change data (3 tools: my_progress, open_study and check_answer), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
5 tools
Changes things 3Claude Code: ask
check_answerGrades the user's choice and returns an explanation for EVERY option, including the ones they did not pick.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Grades the user's choice and returns an explanation for EVERY option, including the ones they did not pick. On this exam two options are frequently defensible and only one is credited, so the reasons the wrong options lose are the part worth teaching.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- revealsAnswerKey: true
my_progressTheir recorded history for one exam, broken down by blueprint domain with the weakest first, plus how their misses compare with everyone else's on the same free-form questions.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Their recorded history for one exam, broken down by blueprint domain with the weakest first, plus how their misses compare with everyone else's on the same free-form questions. Call this at the start of a study session to decide what to drill, and after a run of questions to show what moved. It names the domain to pass to get_practice_question, and when their misses follow the crowd's favorite wrong answers it says to drill those with focus: "traps". Only a signed-in account has history; anonymous callers are told so rather than shown zeros.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
open_studyOpen or resume the study page for an exam, optionally focused on a domain or a sub-objective.1 finding
Why it is in this group
- The name "open_study" says "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "open_study" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "open_study" says "open": a word for a change.
Description, as the server wrote it Open or resume the study page for an exam, optionally focused on a domain or a sub-objective. Use this when someone asks to study rather than to be quizzed in chat: the page gives them a visible question they answer themselves, and once it is open a richer set of tools appears for reading and steering that screen. Returns the URL; a browser agent should navigate there.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
get_practice_questionReturns one original practice question with its options and no answer key.No findings
Why it is in this group
- The name "get_practice_question" says "get": a word for reading.
Description, as the server wrote it Returns one original practice question with its options and no answer key. Present it to the user and let them choose before calling check_answer. Pass every id already served in exclude_ids — this server is stateless and remembers nothing.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_examsThe Claude certifications covered here, with exam codes, item counts, fees and the full domain list with published weights.No findings
Why it is in this group
- The name "list_exams" says "list": a word for reading.
Description, as the server wrote it The Claude certifications covered here, with exam codes, item counts, fees and the full domain list with published weights. Call this first to get valid exam slugs.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:19 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://aicertificates.study/.well-known/oauth-protected-resource
- Authorization servers
- https://clerk.aicertificates.study
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://aicertificates.study/api/mcp: tools/list returned 5 tools to an anonymous client, including my_progress (write), open_study (write), check_answer (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnopen_study
The server marks "open_study" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "open_study" says "open": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:check_answerChanges thingsinputSchema
- Changed:get_practice_questionOnly readsinputSchema
- Changed:my_progressChanges thingsinputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http practice-exams https://aicertificates.study/api/mcpclaude mcp add --transport http practice-exams https://aicertificates.study/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__practice-exams__list_exams",
"mcp__practice-exams__get_practice_question"
],
"ask": [
"mcp__practice-exams__my_progress",
"mcp__practice-exams__open_study",
"mcp__practice-exams__check_answer"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as practice-exams. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/study.aicertificates/practice-exams/verify?hash=90fb04693e0b5d1949d187be4df513642bb1f2c5f3fc05ba927fe87fdb4b01b3" | jq -e '.changed == false'Pinned hash 90fb04693e0b, from Nov 19, 2026, 06:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/study.aicertificates/practice-exams/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/study.aicertificates/practice-exams)Source: MCP Registry. Synced Oct 21, 2026, 18:55 UTC.
AI Certificates MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AI Certificates MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the AI Certificates MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AI Certificates MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the AI Certificates MCP server have?
- 5 tools: 3 write, 2 read. my_progress, open_study, check_answer, list_exams and get_practice_question.
Does the AI Certificates MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AI Certificates MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AI Certificates MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.