_ registry / mcp streamable-http · checked 52m ago

iyt-test

https://iyt.rycrentals.com

Registry code: 3b60408102006b60

api record

IYT Test: practice questions and theory for IYT sailing certification levels, the Racing Rules of Sailing and the charter check-in (6100 questions). Call list_levels first. Ask questions one at a time with options A to D and never reveal the answer before the student chooses; check_answer gives the verdict, the note and the theory section to read. Most questions have a drawing: show figure.url to the student (an SVG image) because the question usually depends on it; if you describe the drawing instead, say what is seen without naming what the question asks. The questions and articles are…

endpoint
https://iyt.rycrentals.com/api/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is iyt-test live?
Yes — it answered the hub's last check (checked 52m ago). It answered 100% of checks over the last 30 days.
Is iyt-test free to use?
Yes — the hub reached it with no key and no payment.
What tools does iyt-test have?
13 tools: get_questions, check_answer, search_questions, start_mock_exam, grade_exam, get_theory, search_theory, explain_question, ….
Is iyt-test safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
297ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 13 tools
3 open 10 never probed 3 of 13 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_levels open 52m ago

    The levels with a question bank (IYT courses, the Racing Rules of Sailing, the charter check-in): topics, number of questions, mock-exam settings and which topics have a theory article. Start here.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • question_of_the_day open 52m ago

    Today's question, the same one the Telegram bot @iyt_test_bot sends: one text question per day (UTC), for one level when a level is given. Without the answer; use check_answer.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "level": {
          "type": "string",
          "description": "Level id from list_levels, e.g. bareboat-skipper."
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • list_theory open 52m ago

    The theory articles: one per topic, each in sections. With a level, the sections of its articles; without, which topics of every level have an article. Articles are still being written, so some topics have none yet.

    mcp-tool

    {
      "type": "object",
      "required": [],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "level": {
          "type": "string",
          "description": "Level id from list_levels, e.g. bareboat-skipper."
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • get_questions unknown never probed

    Random practice questions of a level, without the answers. Ask them one at a time and send the student's choice to check_answer.

    mcp-tool

    {
      "type": "object",
      "required": [
        "level"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "count": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1,
          "description": "How many (default 5)."
        },
        "level": {
          "type": "string",
          "description": "Level id from list_levels, e.g. bareboat-skipper."
        },
        "topic": {
          "type": "string",
          "description": "Topic id, to practise one topic."
        },
        "exclude": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Question ids the student has already had in this conversation, so they are not repeated."
        },
        "text_only": {
          "type": "boolean",
          "description": "Only questions without a drawing, for when images cannot be shown."
        },
        "difficulty": {
          "enum": [
            1,
            2,
            3
          ],
          "type": "integer",
          "description": "1 easy, 2 medium, 3 hard."
        }
      },
      "additionalProperties": false
    }
    arguments 51 lines
  • check_answer unknown never probed

    Checks the option the student chose: right or wrong, the right option, the one-line note that names the rule, and the theory section that explains it (read it with get_theory).

    mcp-tool

    {
      "type": "object",
      "required": [
        "question_id",
        "option"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "option": {
          "enum": [
            "A",
            "B",
            "C",
            "D"
          ],
          "type": "string",
          "description": "The option chosen: A, B, C or D."
        },
        "question_id": {
          "type": "string",
          "description": "Question id, e.g. bs-001."
        }
      },
      "additionalProperties": false
    }
    arguments 32 lines
  • search_questions unknown never probed

    Finds questions by words in the question, its options, its rule reference or its topic (e.g. "cardinal mark", "MAYDAY"). Answers are not included.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "count": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1,
          "description": "How many (default 10)."
        },
        "level": {
          "type": "string",
          "description": "Level id from list_levels, e.g. bareboat-skipper."
        },
        "query": {
          "type": "string",
          "description": "Words to look for; all of them must be there."
        }
      },
      "additionalProperties": false
    }
    arguments 31 lines
  • start_mock_exam unknown never probed

    A mock exam of a level: the exam's number of questions spread evenly over all topics, with the time allowed and the pass mark. No answers until grade_exam: collect the student's choice for every question first.

    mcp-tool

    {
      "type": "object",
      "required": [
        "level"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "level": {
          "type": "string",
          "description": "Level id from list_levels, e.g. bareboat-skipper."
        }
      },
      "additionalProperties": false
    }
    arguments 21 lines
  • grade_exam unknown never probed

    Marks a finished mock exam: the score, pass or fail, the result per topic, every mistake with the right answer and its note, and what to read. Send every question of the exam; one left unanswered has option null and counts as wrong.

    mcp-tool

    {
      "type": "object",
      "required": [
        "answers"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "answers": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "question_id"
            ],
            "properties": {
              "option": {
                "enum": [
                  "A",
                  "B",
                  "C",
                  "D",
                  null
                ],
                "type": [
                  "string",
                  "null"
                ],
                "description": "A, B, C, D, or null when not answered."
              },
              "question_id": {
                "type": "string",
                "description": "Question id, e.g. bs-001."
              }
            },
            "additionalProperties": false
          },
          "maxItems": 100,
          "minItems": 1,
          "description": "One item per question of the exam."
        }
      },
      "additionalProperties": false
    }
    arguments 50 lines
  • get_theory unknown never probed

    A theory article, or one section of it, as text: the rule, the reason, tables and links to the drawings. Study notes close to the syllabus, not official IYT text.

    mcp-tool

    {
      "type": "object",
      "required": [
        "level",
        "topic"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "level": {
          "type": "string",
          "description": "Level id from list_levels, e.g. bareboat-skipper."
        },
        "topic": {
          "type": "string",
          "description": "Topic id from list_theory."
        },
        "section": {
          "type": "string",
          "description": "Section id, to read one section only."
        }
      },
      "additionalProperties": false
    }
    arguments 30 lines
  • search_theory unknown never probed

    Finds the sections of the theory articles that have the words (e.g. "scope", "cardinal marks"). Read a match with get_theory.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "count": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1,
          "description": "How many (default 8)."
        },
        "level": {
          "type": "string",
          "description": "Level id from list_levels, e.g. bareboat-skipper."
        },
        "query": {
          "type": "string",
          "description": "Words to look for; all of them must be there."
        }
      },
      "additionalProperties": false
    }
    arguments 31 lines
  • explain_question unknown never probed

    A question with its answer, the note that names the rule and the full text of the theory section that explains it. This gives the answer away: use it after the student has answered, or when they ask for the explanation.

    mcp-tool

    {
      "type": "object",
      "required": [
        "question_id"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "question_id": {
          "type": "string",
          "description": "Question id, e.g. bs-001."
        }
      },
      "additionalProperties": false
    }
    arguments 21 lines
  • practice_section unknown never probed

    Questions on what a theory section explains: read the section, then practise it. Without the answers; use check_answer.

    mcp-tool

    {
      "type": "object",
      "required": [
        "level",
        "topic",
        "section"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "count": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1,
          "description": "How many (default 5)."
        },
        "level": {
          "type": "string",
          "description": "Level id from list_levels, e.g. bareboat-skipper."
        },
        "topic": {
          "type": "string",
          "description": "Topic id from list_theory."
        },
        "exclude": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Question ids the student has already had in this conversation, so they are not repeated."
        },
        "section": {
          "type": "string",
          "description": "Section id from list_theory."
        }
      },
      "additionalProperties": false
    }
    arguments 44 lines
  • get_figure unknown never probed

    The drawing of a question or of a theory section as SVG markup, for showing it inline where a link to the image is not enough.

    mcp-tool

    {
      "type": "object",
      "required": [
        "figure"
      ],
      "properties": {
        "lang": {
          "enum": [
            "en",
            "ru"
          ],
          "type": "string",
          "description": "Language of the text: en (default) or ru. What is not translated yet comes in English."
        },
        "figure": {
          "type": "string",
          "description": "A question id (bs-001), or a theory drawing as level/topic/section/number (bareboat-skipper/buoyage/lateral/1)."
        }
      },
      "additionalProperties": false
    }
    arguments 21 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 3b60408102006b60.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/3b60408102006b60/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/3b60408102006b60/badge.svg)](https://brick.blue/agent/3b60408102006b60?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

_ also on rycrentals.com 1 entry

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.