# AI Certificates (remote · aicertificates.study)

Practice questions for the four Claude certifications. The assistant never sees the key.

- Trust score: 77/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `aicertificates.study`: 77/100 (this document), [markdown](https://verifymcp.io/servers/study-aicertificates-practice-exams/api-mcp.md), [page](https://verifymcp.io/servers/study-aicertificates-practice-exams/api-mcp)

## Channel facts

- Endpoint: `https://aicertificates.study/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 848 tokens (~169/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 87/100
  - Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the AI Certificates MCP server?

AI Certificates is a hosted endpoint at https://aicertificates.study/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http study-aicertificates-practice-exams 'https://aicertificates.study/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "study-aicertificates-practice-exams": {
      "url": "https://aicertificates.study/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "study-aicertificates-practice-exams": {
      "type": "http",
      "url": "https://aicertificates.study/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.study-aicertificates-practice-exams]
url = "https://aicertificates.study/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "study-aicertificates-practice-exams": {
      "type": "remote",
      "url": "https://aicertificates.study/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add study-aicertificates-practice-exams --url 'https://aicertificates.study/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  study-aicertificates-practice-exams:
    url: "https://aicertificates.study/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "study-aicertificates-practice-exams": {
      "Transport": "http",
      "Url": "https://aicertificates.study/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add study-aicertificates-practice-exams -t streamable-http -u 'https://aicertificates.study/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "study-aicertificates-practice-exams": {
      "type": "http",
      "url": "https://aicertificates.study/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 75, −1)

- [security] Tool “my_progress” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 146 → 169
- [cosmetic] “get_practice_question” added an optional parameter “focus”

### 2026-09-15 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `list_exams` (~42 tokens)

List Claude certification exams

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.

### `get_practice_question` (~186 tokens)

Get a practice question

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.

Input parameters:

- `domain` (string): Optional domain id (e.g. "d3") to drill one area. Domain ids come from list_exams.
- `exam` (string, required): Exam slug from list_exams.
- `exclude_ids` (array): Question ids already served in this session, so they are not repeated.
- `focus` (string): Optional ordering by how everyone else answers these questions: "hardest" serves the highest crowd miss rates first, "traps" serves the questions most people get wrong the SAME way — a shared misconc…

### `my_progress` (~132 tokens)

See what this person has answered so far

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.

Input parameters:

- `exam` (string, required): Exam slug from list_exams.

### `open_study` (~144 tokens)

Open a study session

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.

Input parameters:

- `domain` (string): Optional blueprint domain, e.g. "d3".
- `exam` (string, required): Exam slug from list_exams.
- `sub_objective` (string): Optional concept, e.g. "d1.5". Ids are per-exam.

### `check_answer` (~105 tokens)

Check an answer and explain every option

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.

Input parameters:

- `exam` (string, required): Exam slug.
- `question_id` (string, required): The id from get_practice_question.
- `selected` (array, required): Option letters the user chose, e.g. ["B"] or ["B","D"].

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/study-aicertificates-practice-exams/api-mcp#diagnostics

## Score history

- 2026-09-20: 77
- 2026-09-19: 77
- 2026-09-18: 76
- 2026-09-17: 76
- 2026-09-16: 75
- 2026-09-15: 76
- 2026-09-14: 75
- 2026-09-13: 75
- 2026-09-12: 74
- 2026-09-11: 74
- 2026-09-10: 73
- 2026-09-09: 73
- 2026-09-08: 72
- 2026-09-07: 72
- 2026-09-06: 71
- 2026-09-05: 71
- 2026-09-04: 70
- 2026-09-03: 70
- 2026-09-02: 70
- 2026-09-01: 69
- 2026-08-31: 69
- 2026-08-30: 68
- 2026-08-29: 68
- 2026-08-28: 67
- 2026-08-27: 67
- 2026-08-26: 66
- 2026-08-25: 64

## Common questions

### What is the AI Certificates MCP server?

AI Certificates is an MCP server listed in the public MCP registry as study.aicertificates/practice-exams. Practice questions for the four Claude certifications. The assistant never sees the key. This page covers its hosted endpoint (https://aicertificates.study/api/mcp).

### Is the AI Certificates MCP server safe to use?

AI Certificates scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AI Certificates MCP server expose?

AI Certificates exposes 5 tools: list_exams, get_practice_question, my_progress, open_study, check_answer. Their descriptions and schemas cost roughly 609 tokens of context every time the server is loaded.

### Does the AI Certificates MCP server require authentication?

No. We connected to AI Certificates without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AI Certificates MCP server still maintained?

AI Certificates is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://aicertificates.study/api/mcp
- Website: https://aicertificates.study/mcp
- Changelog RSS feed: https://verifymcp.io/servers/study-aicertificates-practice-exams/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/study-aicertificates-practice-exams/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/study-aicertificates-practice-exams/api-mcp