SchoolScope MCP Server

Compare 2-4 public schools side by side: band, Scope Score, exceeded/met split, cohort growth (aggregate school-by-grade cohorts across the grade span, as a 0-100 index centred on the state average), climate. A school with no cohort comparison reports no growth figure rather than a substitute — treat that as missing evidence, not flat growth. Schools are only comparable within the same level (elementary/middle/high are separate rankings). Private schools cannot be compared — they have no state testing data.

A California district roll-up: average Scope Score and absenteeism across the district plus every scored school ranked by level. Match by district name.

The K-12 feeder path for a school: which schools students typically arrive from, where they go next, and — for elementary/middle schools — the endpoint high school with its graduation and college-going outcomes. Boundary-based (the district's own published boundaries where we have them, else NCES SABS 2015-16), shown alongside scores, never inside them.

The full SchoolScope profile for one school by slug: verdict and archetype, Scope Score with band and percentile per level, CAASPP exceeded/met split, cohort growth (school-by-grade aggregates two years apart, in SBAC scale-score points, reported as a 0-100 index centred on the state average), climate (absenteeism, suspension, ELPAC), equity gaps by student group, teacher stability, and — for high schools — graduation, college destinations, UC admissions history, AP courses, and IB programmes. Also answers "is this school improving?" with a year-over-year table of statewide percentile and the underlying rates; the Scope Score is excluded there because it is normalised within each year and is not comparable across them. For public schools it also returns the profile's own `answer` (one sentence about all students, each subject against California's rate for the same grades), up to three selected `takeaways` (each with figures, comparisons, a question where one applies, and a generated receipt naming source, year, grades, population, n and how the comparison was built), and `studentGroups` (every group by income, race or ethnicity, language and disability with 30+ students tested in each subject, against the same group in the same grades in the district and statewide). Current data year 2026.

Find California schools four ways, whichever fits the question: free text over school/city/district names (`query`), inside a zip code (`zip`), within a radius of a place or coordinate (`near`), or the top-ranked schools at one level (`level` alone). Returns band, Scope Score, archetype and profile URL for each match. Private schools are flagged and never ranked — they have no state testing data. Supply exactly one of query, zip or near; or none plus a level for a top list. Set `tk: true` to limit any of these searches to schools with active transitional kindergarten (TK) enrollment — a filter that composes with query, zip, near and level, and every result carries a `hasTk` field. Set `type` to `charter` to list only charter schools (they admit by application and lottery, not by address), `standard` for district-run public schools, or `private`; like `tk`, it composes with every mode.

Schools serving a similar student population to a given school — same level, comparable free/reduced-lunch share and enrollment size — with the subject's standing among them. This is the fair comparison: a raw ranking largely reflects who enrolls, so a school's position against demographic peers says far more about the school itself than its statewide rank does. Public schools only.

Return the schools the authenticated user has saved on SchoolScope. Requires the `watchlist:read` OAuth scope.