
CertArc MCP server
Which MCP servers are CertArc's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-30
- Registry namecom.certarc/certarcverified in the MCP registry
The registry name sits under certarc.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-30
- Tools12
- Server calls itselfcertarc
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 410 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer585 ms
- Space in an agent's context≈ 2,376 tokensthe definitions of all its tools (12), which an agent carries on every turn
- Tool definitionsA · 97 of 100
- Typed results0 of 12 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 12
What an agent can do with it
- not sure · Review why a chosen exam answer felt right
- not sure · Track recurring wrong-answer habits across practice sessions
- not sure · Rate answer confidence to separate knowledge from guessing
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
practice_questionUse this when someone wants CISM, CISSP, CISA, AAISM, or AAIA practice questions or sample exam questions, or asks for a quiz or to "test me". No account needed. Returns one scenario question from CertArc's free public practice set: the…
check_practice_answerUse this when the learner has chosen an answer to a CertArc practice question. Returns whether it is correct, the correct option and CertArc's explanation for every option. A confident wrong answer is a blind spot. Does not record anything.
get_exam_domainsUse this when someone asks what the CISM, CISSP, CISA, AAISM, or AAIA exam covers. No account needed. Returns the exam domains and their weights, with links to CertArc's public guides and, where it has one, its free practice set. Not for…
search_learning_resourcesUse this when someone asks for CertArc study guides on a topic. Returns published guide titles and links for one certification (the learner's latest when the account is linked). Never returns exam questions or answer keys. Not a general…
open_study_panelUse this when the connected learner wants to see their CertArc study overview: progress, saved schedule and next study option for one certification. Read-only. Not for another learner, exam answers or changing plans.
get_study_patternsUse this when the connected learner asks why they miss questions, where their blind spots are, how their confidence matches their results, or which domains are weakest. Also use it for pace and timing questions. Returns domains weakest…
get_readinessUse this when the connected learner asks about their readiness score, how it is built, how to raise it, or which sprint or exam to retake for the most points. Returns CertArc's Readiness Score with its parts, the points Within reach on…
get_resultsUse this when the connected learner asks how they did on sprints, practice exams, the baseline or the final assessment. Returns each completed one by its CertArc name with Take 1 and Take 2 scores (mode, correct, percent, date), the…
get_result_reviewUse this when the connected learner asks what happened in one sprint or exam: which answers were Incorrect, their confidence, miss reasons, domains, knowledge areas and time per answer, with that take's breakdown by domain, knowledge…
get_study_summaryUse this when the connected learner asks about their CertArc progress. Returns aggregate sprint progress, the target exam date and days to the exam, and the learner's access (Paid, Trial or None and the day it ends) for one certification…
get_study_planUse this when the connected learner asks what to study today or this week, what is overdue, or what is on their CertArc calendar. Returns the calendar as CertArc shows it: every entry with its date and status (Completed, In progress…
get_next_study_actionUse this when the connected learner asks what to study next in CertArc. Returns the next eligible sprint in study order and a link to its domain; the calendar may recommend another. Does not start or complete a session.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"certarc": {
"type": "http",
"url": "https://certarc.com/mcp/claude"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http certarc https://certarc.com/mcp/claudeclaude.ai, ChatGPT and other clients: add https://certarc.com/mcp/claude as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.