
CELPass MCP server
Which MCP servers are CELPass'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 2026-10-28
- Registry namecom.celpass/celpipverified in the MCP registry
The registry name sits under celpass.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools5
- Server calls itselfcelpass
- Server version1.3.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 135 ms.
- Whether its tools do the product's job has not been judged yet.
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 score100 of 100answers 100 · definitions 100 · context 100 · connects 100
- Answered100% of days7 of 7 daily checks
- Median first answer287 ms
- Space in an agent's context≈ 1,082 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Get a predicted CLB score for each CELPIP section
- not sure · Practise timed speaking and writing answers with AI scoring
- not sure · Turn your own mistakes into daily vocabulary and grammar drills
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 →
calculate_crs_november_2026Estimate the CRS points an Express Entry candidate gains on November 3, 2026, when Canadian work experience becomes the Labour Market Integration factor: unchanged work-length points plus 70/40/20 extra points after 12+ months in a…
find_high_wage_occupationSearch IRCC's high-wage occupation list (in effect November 3, 2026; 186 NOC 2021 codes) by job title words or NOC code. Returns each match's level (2×, 1.5× or 1.3× the average median wage) and the CRS points it earns. An occupation that…
get_celpip_practice_questionGet one random CELPIP practice item from CELPass in the real test format. Reading (parts 1–4): a passage or diagram with multiple-choice questions and fill-in blanks shown as ____(n). Listening (parts 1–6): the questions plus a listen_url…
check_celpip_answersMark a learner's answers to a Reading or Listening item from get_celpip_practice_question: returns the score and, for each question the learner answered, whether it is right and the correct letter. Each question_id can be marked once, so…
get_celpip_sample_answersSample answers at several CELPIP levels (4–5, 7–8, 9–10, 11–12) for a Speaking or Writing task from get_celpip_practice_question, with how CELPIP rates it. Use them to give the learner feedback on their own answer.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"celpip": {
"type": "http",
"url": "https://celpass.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http celpass https://celpass.com/mcpclaude.ai, ChatGPT and other clients: add https://celpass.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.
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.