Quantabble — AP Science Misconception Diagnostics

Official2 toolsLive

by Quantabble

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

MCP Server: io.github.Quantabble/ap-science-diagnostics

This MCP server provides misconception detection for AP Chemistry and Physics 1. It reports a 90% catch rate compared to a 24% baseline. The server exposes two tools, as indicated by its toolCount.

🛠️ Key Features

Misconception detection for AP Chemistry & Physics 1
Catch-rate reporting: 90% vs 24% baseline
2 available tools

🚀 Use Cases

Identify misconceptions in AP Chemistry and Physics 1 learning content
Compare detection performance against a stated baseline

⚡ Developer Benefits

Small, tool-based integration surface (2 tools)
Clear performance metric for detection (90% vs 24%)

⚠️ Limitations

Supported scope is limited to AP Chemistry and Physics 1
Only a catch-rate metric is described (no additional evaluation details provided)

Captured live from the server via tools/list.

diagnose_response

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 the specific misconception in their reasoning, severity, confidence score, a ready-to-deliver tutor response, a follow-up probe question, and a step-by-step remediation plan. Use this whenever a student writes an explanation and you need to know what they misunderstand and exactly what to say next. Do not use for single-word or number-only answers.

Parameters2

student_response	string	required	The student's own words — their explanation, reasoning, or answer in free-response form. At least one complete sentence with a stated reason works best.
schema_id	string	optional	Optional. Target a specific schema (e.g. "AP_CHEM_1_1") if you already know the topic. If omitted, the API routes automatically across all 130 schemas.

Raw schema

{
  "type": "object",
  "properties": {
    "student_response": {
      "type": "string",
      "description": "The student's own words — their explanation, reasoning, or answer in free-response form. At least one complete sentence with a stated reason works best."
    },
    "schema_id": {
      "type": "string",
      "description": "Optional. Target a specific schema (e.g. \"AP_CHEM_1_1\") if you already know the topic. If omitted, the API routes automatically across all 130 schemas."
    }
  },
  "required": [
    "student_response"
  ]
}

get_coverage

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.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "required": []
}

Install

Tools (2)

diagnose_responseget_coverage

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://quantabble-api.chemandphysicsmastery.workers.dev

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "ap-science-diagnostics": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://quantabble-api.chemandphysicsmastery.workers.dev"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.