AQ School knowledge graph

Ask how the platform
fits together.

Lore maps every AQ School app (its entities, APIs, events, datastores and flows) and the links between them. It's built from the code and served over MCP, so your coding agent can look things up instead of guessing across a dozen repos.

13apps mapped
3,003nodes
1,008cross-app links

Connect

Read-only, and the same graph for every client. You'll need the shared API token; ask the owner if you don't have it.

Claude Code plugin Recommended

Wires up the MCP server and adds skills built on it, like /blast-radius for cross-app impact analysis.

export KG_API_TOKEN=…
claude plugin marketplace add pearson-aq-school/lore
claude plugin install lore-kg@lore

Any MCP client

Streamable HTTP at /api/mcp, authenticated with a bearer token.

claude mcp add --transport http lore-kg \
  https://aq-88c13488a7544e4da8927f1a6312e1a9.ecs.us-east-1.on.aws/api/mcp \
  --header "Authorization: Bearer $KG_API_TOKEN"
How does an item in Abigail relate to the item in AD?
Which apps are affected if the AD host callback payload changes?
Who can publish or retire items in a bank, and what code checks it?

Tools

Start with search, open a hit with node, then traverse. Nodes whose status isn't active are legacy, deprecated or planned.

search

Find nodes by exact id, alias, or full text across every app.

node

Everything about one node: fields, typed and cross-app edges, source links, Markdown body.

neighbors

What surrounds a node, k hops out, across app boundaries.

path

The shortest route between any two nodes, even in different apps.

permissions

Who can do what, and which code enforces it.

id_map

Where an entity's id is stored in other apps.

sql

Read-only DuckDB SQL over nodes, edges, fields and sections, for anything else.

Resources

kg://node/{qid} for a node's raw Markdown, kg://readme/{app} for an app's overview.

Graphs

Each app has an interactive graph, a README overview and a node index. The system graph shows how they connect.

systemCross-app

94 nodes

Thirteen app graphs linked into one system: ad (Authoring & Delivery — items, forms, the test player, scoring), abigail (item bank / review front end over AD), adam (ass…

abigail

295 nodes

Abigail is Pearson's summative-assessment layer on top of the Authoring & Delivery (AD) platform ("AD" means Authoring & Delivery, not Active Directory).

ad

214 nodes

AD is Pearson's assessment platform.

adam

528 nodes

ADAM (Assessment Delivery and Management) is a Go/Gin monolith plus four Vue apps that rosters K-12 tenants, sets up tests and administrations, delivers them (AD player…

arc

145 nodes

ARC (Assessment Resource Connector) is Pearson's LTI 1.3 tool that sits between school LMSs and the AD (Authoring & Delivery) test engine.

cf

79 nodes

Continuous Flow (repo ktcf-continuous-flow, Go module git.pearsonkt.com/111/111-continuous-flow) is Pearson Knowledge Technologies' automated constructed-response scorin…

cow

328 nodes

COW ("Core Warehouse", also called Assessment-as-a-Service / PWS) is Pearson's assessment-data warehouse and extract platform.

lp

215 nodes

LaunchPad is Pearson's OneRoster 1.2 rostering and identity-federation platform for K-12.

mot

128 nodes

MOT (Materials Order Tracking) is the configuration app that materials planners and order operations staff use to set up what physical test materials a testing program s…

mre

85 nodes

The MRE (Math Response Engine) is the KT math scoring engine: a Python 3 / Flask service built on SymPy that scores constructed math responses.

navvy

254 nodes

Navvy Classroom (pearson-aq-school/navvy_classroom) is a K-12 classroom assessment app.

oscar

398 nodes

OSCAR (Online Scoring and Reporting) is where open-ended student responses get scored.

psaes

179 nodes

PSAES (Pearson Scan and Assessment Engineering System) is where Pearson's scanning team engineers the paper answer documents that get scanned.

xprt

61 nodes

XPRT (XML Print Rendering Tool, repo xprt-app) is a thin Java service in front of a Typefi composition server (InDesign Server based).