
KeenIELTS MCP server
Which MCP servers are KeenIELTS'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 2026-10-19
- Registry namecom.keenielts/mcpverified in the MCP registry
The registry name sits under keenielts.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-19
- Tools9
- Server calls itselfKeenIELTS
- Server version1.12.4
- Protocol version2025-06-18
On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 150 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- For "study model answers written by students", the likely first call is search_model_answers.
- Parameters are untyped or undescribed in 8 of 9 tools: check arguments before calling.
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 score90 of 100answers 100 · definitions 69 · context 100 · connects 100
- Answered100% of days16 of 16 daily checks
- Median first answer238 ms
- Space in an agent's context≈ 1,439 tokensthe definitions of all its tools (9), which an agent carries on every turn
- Tool definitionsC · 69 of 100
- Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 8 of 9
- Not saying whether it only reads or can destroy: 9 of 9
What an agent can do with it
- not sure · get band scores and examiner-style feedback on practice answers
- can do · study model answers written by students
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 →
search_model_answersSearch real student IELTS Writing answers scored by AI examiner. Args: task: IELTS Writing task number — 1 (reports/letters) or 2 (essays). band: whole band to filter on; matches half-bands too (8 -> 8.0-8.5). query: free-text match…
get_model_answerGet one student IELTS Writing answer in full: the question, the essay, and the AI examiner's band scores + feedback on all four official IELTS marking criteria (Task Achievement, Coherence & Cohesion, Lexical Resource, Grammatical Range &…
compare_questionList every public band-scored answer to ONE IELTS Writing question — the same prompt answered by different students at different band scores, useful for showing what separates a Band 6 from a Band 8 on identical input. Fetch individual…
list_drillsList short, targeted IELTS practice drills that can be taken right here in the conversation (fetch with get_drill, grade with check_drill_answers). Args: skill: 'listening' or 'reading'. category: optional IELTS question-type filter…
get_drillGet one drill's content so the user can attempt it in conversation. The questions are markdown; `{{3}}` marks a gap the user fills for question 3, and `{{3:A/B/C}}` means question 3 is a choice between the slash-separated options. For…
check_drill_answersGrade a user's drill answers server-side (same grader the website uses — case/whitespace tolerant, accepts standard IELTS answer variants). Args: skill: 'listening' or 'reading'. slug: the drill slug from get_drill. answers: question…
list_practice_testsCatalog of full-length IELTS practice tests on keenielts.com — books, difficulty, and test counts for all four skills (Listening, Reading, Writing, Speaking). Full tests are taken on the website (timed, with audio players and AI band…
searchSearch KeenIELTS: real student IELTS Writing model answers with band scores, Listening/Reading practice drills, and IELTS practice resources. Returns result ids for use with fetch.
fetchFetch the full content of a KeenIELTS search result by id: a model answer with examiner feedback, a practice drill, a question compared across band scores, or a site page.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"keenielts": {
"type": "http",
"url": "https://keenielts.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http keenielts https://keenielts.com/mcpclaude.ai, ChatGPT and other clients: add https://keenielts.com/mcp 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.