Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.
exam.now is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Cambridge, AQA and Edexcel past papers: questions, figures and mark schemes by part, and marking.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http exam-now-mcp https://exam.now/mcp
# 2 — ask your agent for something these tools do
# find_past_paper, get_question, get_mark_scheme and 8 more
exam.now costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http exam-now-mcp https://exam.now/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
11 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Find Cambridge, AQA or Edexcel past papers on exam.now from a free-text query such as "0580 june 2024 paper 4" or from structured fields. Returns up to 10 papers with their exam.now paper_id, title, session, duration, total marks, whether it can be answered on screen, and links to the question paper, mark scheme and examiner report. Use the paper_id with get_question, get_mark_scheme or get_paper.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Free text, e.g. "0625 w23 42" or "igcse physics november 2023 paper 4". |
| board | string | no | — |
| qualification | string | no | e.g. "IGCSE", "O Level", "A Level", "GCSE". |
| subject_code | string | no | Syllabus or specification code, e.g. 0580, 0625, 9709, 8300 or 1MA1. |
| year | integer | no | — |
| series | string | no | Exam series. |
| paper | integer | no | — |
| variant | integer | no | — |
| limit | integer | no | — |
The text of one question or part from an exam.now past paper: context, prompt, marks, figures (with alt text), the answer surface (response kinds, tools, whether a calculator is allowed), topic codes and a link to the part on exam.now. Pass question for the whole question or part for one part.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paper_id | string | yes | exam.now paper id from find_past_paper, e.g. 0580_s24_42 (syllabus code, series letter s/w/m and two-digit year, component). |
| question | string | no | Question number, e.g. "3". |
| part | string | no | Part id as the paper numbers it, e.g. "3", "3(a)" or "3(a)(i)". |
| include_images | boolean | no | Attach small figures as image content as well as URLs. |
The official mark-scheme rows for one part of an exam.now past paper: each row's code (M1, A1, B1…), marks, answer, guidance and alternatives, the part's maximum marks, the paper's general marking principles, the mark-scheme PDF page and a link to it on exam.now.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paper_id | string | yes | exam.now paper id from find_past_paper, e.g. 0580_s24_42 (syllabus code, series letter s/w/m and two-digit year, component). |
| part | string | yes | Part id as the paper numbers it, e.g. "3", "3(a)" or "3(a)(i)". |
| include_principles | boolean | no | Include the paper's general marking principles. |
An exam.now past paper as structured JSON (metadata, questions, parts, prompts, marks, answer kinds, figure URLs), a few questions at a time. Use next_from to get the next page. include_mark_scheme adds the mark-scheme rows for the same questions and needs a linked exam.now account (a free one is fine).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paper_id | string | yes | exam.now paper id from find_past_paper, e.g. 0580_s24_42 (syllabus code, series letter s/w/m and two-digit year, component). |
| from_question | integer | no | First question to return (1-based position in the paper). |
| count | integer | no | How many questions to return. |
| include_mark_scheme | boolean | no | — |
Past-paper questions on exam.now tagged with a syllabus topic, newest first. Pass the topic code (e.g. E2.5) or words (e.g. "simultaneous equations"). Returns question references with the start of each prompt, marks, whether it has a figure, and a link to the question.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject_code | string | yes | Syllabus or specification code, e.g. 0580, 0625, 9709, 8300 or 1MA1. |
| topic | string | yes | Topic code or words. |
| limit | integer | no | — |
Show one past-paper question as a practice card the student can answer, with its figures and answer surface. The model gets the full question so it can give hints without giving the answer away. Use mark_answer to mark the student's answer.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paper_id | string | yes | exam.now paper id from find_past_paper, e.g. 0580_s24_42 (syllabus code, series letter s/w/m and two-digit year, component). |
| question | string | no | Question number, e.g. "3". |
| part | string | no | Part id as the paper numbers it, e.g. "3", "3(a)" or "3(a)(i)". |
Mark a student's answer to one part against the official mark scheme with exam.now's marker. Returns marks awarded and available, the mark-scheme rows earned and missed, feedback and a common-mistake link, and saves the mark to the student's exam.now progress. Needs a linked exam.now account with marking.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paper_id | string | yes | exam.now paper id from find_past_paper, e.g. 0580_s24_42 (syllabus code, series letter s/w/m and two-digit year, component). |
| part | string | yes | Part id as the paper numbers it, e.g. "3", "3(a)" or "3(a)(i)". |
| answer | string | yes | The student's final answer, as they wrote it. |
| working | string | no | The student's working, if any. |
The linked student's own progress in one subject on exam.now: each syllabus topic's band (secure, getting there, not yet), the next three topics to work on and links to practise them.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject_code | string | yes | Syllabus or specification code, e.g. 0580, 0625, 9709, 8300 or 1MA1. |
Cambridge exam dates for one or more syllabuses in the June or November 2026 series: component, date, morning or afternoon session and duration, with a link to the exam.now timetable. Zone defaults to the UK timetable.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject_codes | array | yes | — |
| series | string | yes | — |
| zone | string | no | Cambridge administrative zone. |
Up to 5 exam.now write-ups of common mistakes in a subject, drawn from Cambridge examiner reports, each with a short summary and a link. Narrow them with a topic code or words.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject_code | string | yes | Syllabus or specification code, e.g. 0580, 0625, 9709, 8300 or 1MA1. |
| topic | string | no | Topic code, e.g. E1.10. |
| query | string | no | Words to match, e.g. "bounds". |
For a teacher's own exam.now class: topic bands across the class with no pupil names, and how many pupils have started. Small groups are suppressed to protect pupils' privacy.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject_code | string | yes | Syllabus or specification code, e.g. 0580, 0625, 9709, 8300 or 1MA1. |
| class_id | string | no | The class id from exam.now. Leave it out for the teacher's own class. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install exam.now or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| find_past_paper | no tags | |
| get_question | no tags | |
| get_mark_scheme | no tags | |
| get_paper | no tags | |
| find_questions_by_topic | no tags | |
| practise_question | no tags | |
| mark_answer | state-write | state-write: declares readOnlyHint: false |
| topic_progress | no tags | |
| exam_timetable | no tags | |
| common_mistakes | no tags | |
| class_summary | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish exam.now can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.