# Quantabble — AP Science Misconception Diagnostics

> Misconception detection for AP Chemistry & Physics 1. 90% catch rate vs 24% baseline.

- name: io.github.Quantabble/ap-science-diagnostics
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 69/100 flags: no-repository
- quality: 65/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Quantabble%2Fap-science-diagnostics
- tools: https://api.protogrid.dev/v1/servers/io.github.Quantabble%2Fap-science-diagnostics/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ap-science-diagnostics": {
      "type": "http",
      "url": "https://quantabble-api.chemandphysicsmastery.workers.dev"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 65
- provenance: 35
- drivers: +reachable +uptime-97% ~updated-105d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 65/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: diagnose_response (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_coverage (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 528 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 528 tokens to load them all
- tool set hash: 9e3d382d3a06861d1ed4e29f5104fe5d
- tools last changed: 2026-10-03T13:35:33.902Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Quantabble/ap-science-diagnostics.svg)](https://protogrid.dev/servers/io.github.Quantabble/ap-science-diagnostics)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-03 `get_coverage` changed (description) **meaning changed**
  - before: Returns the list of subjects and unit counts covered by Quantabble. Use this to check whether a student's topic is within scope before calling diagnose_response.
  - after: Returns Quantabble's coverage and full topic catalog: every schema_id with its course, unit, topic number and title. Use it to check a topic is in scope and to look up the schema_id to pass to diagnose_response when you already know what the student is working on. Free; no model call.
- 2026-10-03 `diagnose_response` changed (description) **meaning changed**
  - before: Evaluate a student's written explanation in AP Chemistry, AP Physics 1, high school chemistry, high school physics, college chemistry, or college physics (algebra-based). Returns whether a misconception was detected in their reasoning, a ready-to-deliver tutor response you can say to the student verbatim, and a follow-up probe question to ask next. Use this whenever a student writes an explanation and you need to know what to say next. Do not use for single-word or number-only answers.
  - after: Diagnose a student's written explanation in AP Chemistry or AP Physics 1 (or the same topics in introductory chemistry or algebra-based physics). Returns structured diagnostic data for your own tutoring: the verdict; the student's specific misconception in plain words, with error_source telling you whether it comes from our curated misconception library or was identified by the engine; where the topic sits in the AP course (unit and topic); why this reasoning loses credit on AP-style free-response scoring; what a credit-earning explanation must include; a recommended teaching move; and one probe question. A short ready-to-use tutor_response is included for simple integrations. Each response includes schema_id, the topic it matched: pass it back as schema_id on follow-up calls about the same topic to skip topic routing (faster and more consistent), and use it with curriculum_anchor to organize practice and reports by unit and topic. Use error_name to describe the error to teachers and students. Treat teaching_guidance as a recommendation, and prefer the probe question over reading reader_trap to the student verbatim. Send at least one full sentence of reasoning; not for single-word or numeric answers. Not affiliated with or endorsed by the College Board.

Full history: https://api.protogrid.dev/v1/servers/io.github.Quantabble%2Fap-science-diagnostics/changes

## Remotes

- https://quantabble-api.chemandphysicsmastery.workers.dev (streamable-http, auth none, reachable true, uptime30d 0.973913)

## Packages

_none_

## Tools (2)

- `diagnose_response`: Diagnose a student's written explanation in AP Chemistry or AP Physics 1 (or the same topics in introductory chemistry or algebra-based physics). Returns structured diagnostic data for your own tutoring: the verdict; the student's specific misconception in plain words, with error_source telling you whether it comes from our curated misconception library or was identified by the engine; where the topic sits in the AP course (unit and topic); why this reasoning loses credit on AP-style free-response scoring; what a credit-earning explanation must include; a recommended teaching move; and one probe question. A short ready-to-use tutor_response is included for simple integrations. Each response includes schema_id, the topic it matched: pass it back as schema_id on follow-up calls about the same topic to skip topic routing (faster and more consistent), and use it with curriculum_anchor to organize practice and reports by unit and topic. Use error_name to describe the error to teachers and students. Treat teaching_guidance as a recommendation, and prefer the probe question over reading reader_trap to the student verbatim. Send at least one full sentence of reasoning; not for single-word or numeric answers. Not affiliated with or endorsed by the College Board.
- `get_coverage`: Returns Quantabble's coverage and full topic catalog: every schema_id with its course, unit, topic number and title. Use it to check a topic is in scope and to look up the schema_id to pass to diagnose_response when you already know what the student is working on. Free; no model call.