MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Other

WaterExamMath

Math practice for the California water operator exams (T1-T3, D1-D3) with worked solutions.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
550 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
10

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 550 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name waterexammath.

  • Pass
    Lists tools

    tools/list returned 10 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 550 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 550 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    23 of 23 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-09T22:05:03.210112Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using WaterExamMath

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http waterexammath https://waterexammath.com/mcp

Capabilities

Tools 10

check_answer

Check the learner's answer to one practice problem and record it, or several problems at once with `answers` (up to 20 pairs of problem id and letter). Returns, per problem, whether it was correct, the correct option, the worked solution and the cited conversion sheet line. The problem id identifies its exam (grade). Side effects: creates the learner's account on first use, saves the attempt to the learner's progress for that grade (mastery per topic and the review schedule; missed problems come back later) and adds a usage record. Overwrites and deletes nothing. Limit: at most 40 answers per minute per account; over it, nothing is recorded and the call can be retried a moment later. Calling it again for the same problem records another attempt, so call it once per answer the user gives. Problems that are part of an open timed set can't be checked until that set is submitted.

Discovered
get_exam_overview

Describe a California drinking water operator exam (grade): what the math covers by topic, the timed practice set format, the size of the problem bank and the official sources (including the CA Exam Conversion Sheet). Without exam and before the user has chosen a grade, lists every available grade with its id. Works signed out. Read-only; changes nothing.

Discovered
get_progress

Show the learner's readiness for one exam (grade), overall and per topic (accuracy, number answered, last practiced), how many problems are due for review, the exam date if set, and suggested next steps. Read-only; changes nothing.

Discovered
get_study_plan

Build a day-by-day math study plan for one exam (grade) up to the exam date from the learner's current mastery: daily practice weighted to weak topics, review of missed problems, timed sets and rest days. Uses the exam date saved in WaterExamMath for that grade (save_study_settings saves one); pass examDate (YYYY-MM-DD) to plan for a different date. The date passed here is not saved. Read-only; changes nothing.

Discovered
practice_questions

Get a set of math practice problems WITHOUT their answers, chosen for this learner in one exam (grade): problems they missed come back first, and weak, heavily weighted topics get more problems. Returns each problem's id, topic, text and lettered options (1 to 20 per call, default 5). Optionally limit to one topic by its id from get_exam_overview. Read-only: nothing is recorded until check_answer. Each call may return a different set.

Discovered
reset_progress

Permanently erase the learner's progress for one exam (grade): every recorded answer, mastery per topic, the review schedule and all timed set results for that grade. Other grades are not touched. This cannot be undone. Requires confirm: true, meaning the user explicitly asked to reset and confirmed which grade. The exam date and account stay. Each call also adds a usage record; repeating it erases nothing more.

Discovered
save_mock_answers

Save some or all answers of an OPEN timed set from start_mock_exam as a draft, by problem number (1-based) and letter. Only the listed problems change; the others keep their saved answer. Any answer can be changed again until the set is submitted (send a new letter, or an empty string to leave that problem blank again), so nothing is lost by saving. Nothing is scored and nothing is recorded into the learner's progress until submit_mock_exam. Returns how many problems are answered and which numbers are still blank. Side effects: updates the unsubmitted draft on that one open timed set and nothing else. Safe to retry: the same answers give the same draft. Only submit_mock_exam makes the answers final.

Discovered
save_study_settings

Save the learner's grade and, optionally, their exam date and daily problem target for that grade, so later calls default to that grade and get_study_plan uses that date. Side effects: creates the learner's account on first use and REPLACES the saved grade (and the saved exam date or daily target for that grade, when given) with these values. Practice history is not touched. Safe to retry: the same values give the same result.

Discovered
start_mock_exam

Start a timed math set for one exam (grade): problems spread over its math topics, with a time limit. Optional `count` (10, 25 or 50 problems, default 25) and `minutes` (15, 30, 60, 90 or 120, default 60). It covers the math portion only. Returns the set id, the deadline and every problem WITHOUT answers; submit_mock_exam scores all answers at once. Side effects: creates the learner's account on first use, a timed set record and a usage record. If a set is already open for that grade (even past its deadline) that set is returned instead and nothing new is created; after it is submitted, calling again starts a new one. Nothing is closed or cancelled by this call. A set left open more than 7 days past its deadline is closed without a score by a daily cleanup. Timed sets are not limited per month; at most 12 new timed sets can be started per hour per account (over it, nothing is created and the call can be retried later).

Discovered
submit_mock_exam

Submit a timed set from start_mock_exam and get the score report: total, whether it reached the target, score per topic, and the missed problems with worked solutions and sources. Without `answers`, the draft saved with save_mock_answers is submitted. With `answers`, they are letters in problem order, one per problem; use an empty string for a skipped problem. Skipped problems count as wrong. Submitting is final (marked destructive for that reason): the set closes and its answers can't be changed afterwards, so ask the learner once before calling it. A set submitted after its deadline is still scored and marked late. Side effects: closes the timed set, records the answers into the learner's progress for that grade (a crew supervisor the learner joined sees them in practice stats) and adds a usage record. Safe to retry: submitting the same set again returns the stored result and records nothing more.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected550 ms10