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 · Knowledge & memory

SchoolScope

California school data for AI agents — scores, comparisons, feeder paths, TK ages, applications.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
594 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

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

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 594 ms.

  • Pass
    Valid handshake

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

  • 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 594 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 594 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

    19 of 21 parameters have a description (90%). 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 2026-11-03T07:07:56.595087Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using SchoolScope

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 schoolscope https://mcp.schoolscope.co/mcp

Capabilities

Tools 10

compare_schools

Compare 2-4 public schools side by side: band, Scope Score and percentile, exceeded/met split, cohort growth (aggregate school-by-grade cohorts across the grade span, as a 0-100 index centred on the state average), and CDE's reported chronic absenteeism and suspension rates, each labelled with its year. High schools add graduation, a-g completion, college-going, UC admissions, AP courses and IB programmes. A school with no cohort comparison reports no growth figure rather than a substitute; that is 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.

Discovered
district_profile

A California district roll-up, level by level: each level's average Scope Score, percentile, exceeded-standard share and CDE chronic absenteeism across its comprehensive schools, and every scored school ranked within its level. Elementary, middle and high are never averaged or ranked together. Continuation and alternative schools are listed apart, unnumbered, because they are ranked only within their own peer class. Match by district name.

Discovered
feeder_path

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.

Discovered
find_schools

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.

Discovered
my_applications

The authenticated user's SchoolScope application tracker for 2027–28, in the order schools were added: each school's door (how it takes applications), status, the nearest upcoming published application date with the page it was read from, the family's own upcoming dates, and their note. Requires the `applications:read` OAuth scope.

Discovered
my_watchlist

The schools the authenticated user has saved on SchoolScope, newest first, each with its band, Scope Score and percentile at its lead level and the nearest upcoming published application date with the page it was read from. Private schools are listed unscored. Requires the `watchlist:read` OAuth scope.

Discovered
school_profile

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.

Discovered
similar_schools

Schools serving a similar student population to a given school — same level, same peer class, 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.

Discovered
start_age

Which school year a California child is transitional kindergarten (TK) or kindergarten age, from a birth month and year, under California Education Code § 48000 (TK: fourth birthday by September 1; kindergarten: fifth birthday on or before September 1). The birth day matters only in September, where September 1 and September 2–30 fall on different sides of the cutoff; without it, both outcomes are given. With a district, it adds that district's upcoming choice-window dates SchoolScope holds.

Discovered
track_application

Adds a school to the authenticated user's SchoolScope application tracker, or changes the status or note of a school already on it. A new entry takes the school's door and how-to-apply line from SchoolScope's record and starts at "planning" ("Planning to apply") unless a status is given. It changes the user's saved list. Statuses, in order: planning ("Planning to apply"), applied ("Applied"), confirmed ("Confirmation checked"), waiting ("Waiting for the lottery or letter"), offer ("Offered a seat"), waitlisted ("Waitlisted"), accepted ("Accepted"), declined ("Declined"). A list holds at most 30 schools. Requires the `applications:write` OAuth scope.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected594 ms10