# Words in Context > A bank of words-in-context practice questions: a real sentence, four plausible options, and an explanation of why the right answer fits and why each distractor does not. Built for the current digital SAT format, which tests inference from context rather than memorised definitions. Optionally generate extra questions from your own reading or your own missed words. Four surfaces over one engine: an HTML page for people, a markdown representation of every page at the same URLs, a JSON API, and an MCP server. All four return the same answers — the engine is a single pure function and the surfaces are thin wrappers over it. For markdown, send `Accept: text/markdown` or append `?format=md` to any page URL. Responses set `Vary: Accept`. Do not parse the HTML. **What this is not:** Not affiliated with or endorsed by the College Board, and not a source of official practice tests. Does not track scores across devices or hold an account — progress stays in your own browser. Agent traffic is welcome and unmetered up to 250 calls per UTC day per caller. Past that, endpoints return HTTP 402 with x402 payment requirements ($0.001 per call, USDC on base). Content is identical for agents and people; only the representation differs. ## Agent endpoints - [MCP server](https://words-in-context.gumballtools.com/api/mcp): Streamable HTTP. Tools: draw_items, check_answer, generate_items. - [OpenAPI document](https://words-in-context.gumballtools.com/.well-known/openapi.json): Full machine-readable API description. - [Run the tool](https://words-in-context.gumballtools.com/api/v1/draw?count=5&difficulty=core): the primary endpoint. - [Full documentation](https://words-in-context.gumballtools.com/llms-full.txt): Complete docs with worked examples, inline. - [Changelog](https://words-in-context.gumballtools.com/changelog.md): Breaking changes and additions. ## MCP tools ### `draw_items` Draw words-in-context vocabulary practice questions from a curated, human-written bank. Use this to quiz a learner, build a practice set, or check what a question of this type looks like. It is free, deterministic, and costs no inference. IMPORTANT: the response deliberately contains NO answer index and NO explanations. That is so you can present the questions without leaking the answers. Call `check_answer` with the item id and the chosen option to get the answer, why it fits, and why each distractor fails. Input: `count` (1-20, default 5) — an out-of-range count is REFUSED rather than clamped, so you learn the limit. `difficulty` is foundation|core|stretch. `theme` is science|humanities|social-science|literature. `seed` makes the draw reproducible: the same seed always returns the same items, so a practice session can be replayed or shared. Format note: these test inference from context, which is how the current digital SAT asks about vocabulary — not recall of definitions. Each item is a sentence with one word blanked and four options. ### `check_answer` Check an answer to a practice item and get the teaching content. Returns whether the choice was correct, which option was right, why it fits the sentence specifically, why the chosen option was wrong, and the reason EVERY distractor fails. Read the distractor reasons out to the learner even when they answered correctly. Knowing why the tempting wrong answer was tempting is the part that transfers to the next question; being told "correct" teaches nothing. Input: `id` from a draw response, and `choice` as the zero-based index of the selected option. ### `generate_items` Generate new practice items from a passage the learner supplies — their own reading, or the material they got wrong. This is the PAID tier and it costs real money per call, unlike the curated bank. Prefer `draw_items` unless the learner specifically needs questions from their own material. `model` is a priced choice: "economy" at $0.002 per item (Fast and cheap. Good enough for straightforward vocabulary in clear prose.); "standard" at $0.008 per item (Better at writing distractors that are genuinely tempting, which is the hard part of a good practice item.). Pick economy for straightforward prose and standard when the distractors need to be genuinely tempting, which is the hard part of a good question. Limits: passage 200 characters minimum, and `count` at most 5 per call. Generation is capped at 10 calls per caller per day, separately from the free quota. Generated items are NOT reviewed by a person. Every response carries a caveat saying so. Check the answer and the distractor reasons before giving them to a learner — a generated question with two defensible answers is worse than no question. Returns 503 when generation is not enabled on the deployment; fall back to `draw_items`. ## Markdown representations Every page is available as markdown at the same canonical URL. Send `Accept: text/markdown` or append `?format=md`. Responses set `Vary: Accept`. Do not parse the HTML. ## Docs - [Documentation and MCP setup](https://words-in-context.gumballtools.com/docs): Copy-paste MCP config for Claude Code, Claude Desktop, and Cursor, plus curl examples. ## Pages - [Words in Context](https://words-in-context.gumballtools.com/): Practise the vocabulary questions the way the test actually asks them - [API and MCP setup](https://words-in-context.gumballtools.com/docs): JSON API reference and MCP configuration - [Every practice question](https://words-in-context.gumballtools.com/practice/all-questions): The whole bank, with the answer and the reason each distractor fails. - [Foundation questions](https://words-in-context.gumballtools.com/practice/foundation): Start here. The context clue is close to the blank and points one way. - [Core questions](https://words-in-context.gumballtools.com/practice/core): The level most of the test sits at, where at least one distractor is genuinely tempting. - [Stretch questions](https://words-in-context.gumballtools.com/practice/stretch): Harder items where the wrong answers are near-synonyms with the wrong connotation. - [Science passage vocabulary](https://words-in-context.gumballtools.com/practice/science-passages): Words as they appear in scientific writing — hedging, evidence, and causation. - [Humanities passage vocabulary](https://words-in-context.gumballtools.com/practice/humanities-passages): Words for argument, interpretation, and scholarly disagreement. - [Social science passage vocabulary](https://words-in-context.gumballtools.com/practice/social-science-passages): Words for policy, method, and the gap between a stated aim and a real one. - [Literature passage vocabulary](https://words-in-context.gumballtools.com/practice/literature-passages): Words for character, tone, and the way a narrator reveals or conceals. - [Words about evidence](https://words-in-context.gumballtools.com/practice/words-about-evidence): Corroborate, undermine, anomalous, plausible — how writers signal how much to trust a claim. - [Words about certainty and doubt](https://words-in-context.gumballtools.com/practice/words-about-certainty): Tenuous, inevitable, contingent, ostensibly — the vocabulary of how sure a writer is.