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.
Read-only, and the same graph for every client. The first tool call opens a browser sign-in page: paste the shared access token once (ask the owner if you don't have it) and your client stays logged in.
Wires up the MCP server and adds skills built on it, like /blast-radius for cross-app impact analysis. To stay current, turn on auto-update in /plugin → Marketplaces → lore.
claude plugin marketplace add pearson-aq-school/lore claude plugin install lore-kg@lore
The same plugin, from the Copilot CLI. VS Code Copilot picks it up too, or add "chat.plugins.marketplaces": ["pearson-aq-school/lore"] to settings and install lore-kg from the Extensions view (@agentPlugins).
copilot plugin marketplace add pearson-aq-school/lore copilot plugin install lore-kg@lore
Streamable HTTP at /api/mcp, with OAuth sign-in. Scripts can send Authorization: Bearer <token> instead.
claude mcp add --transport http lore-kg \ https://aq-school-lore.pearsondev.tech/api/mcp
Start with search, open a hit with node, then traverse. Nodes whose status isn't active are legacy, deprecated or planned.
searchFind nodes by exact id, alias, or full text across every app.
nodeEverything about one node: fields, typed and cross-app edges, source links, Markdown body.
neighborsWhat surrounds a node, k hops out, across app boundaries.
pathThe shortest route between any two nodes, even in different apps.
permissionsWho can do what, and which code enforces it.
id_mapWhere an entity's id is stored in other apps.
sqlRead-only DuckDB SQL over nodes, edges, fields and sections, for anything else.
kg://node/{qid} for a node's raw Markdown, kg://readme/{app} for an app's overview.
Bundled with the plugin. Each one runs on the tools above and cites the graph nodes behind every answer.
/blast-radiusWhich other apps and cross-app flows a branch, PR or story affects, and what to coordinate.
/contract-checkField by field: does a change break an API, payload or mapped field another app consumes?
/onboardOne-page orientation to an app: core entities, entry points, flows, who it talks to, what's legacy.
/where-doesWhere a piece of data is owned, stored, copied and moved across apps.
/trace-flowHop-by-hop walk of an end-to-end flow, written to Markdown with Mermaid diagrams.
Each app has an interactive graph, a README overview and a node index. The system graph shows how they connect.
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 is Pearson's summative-assessment layer on top of the Authoring & Delivery (AD) platform ("AD" means Authoring & Delivery, not Active Directory).
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 (Assessment Resource Connector) is Pearson's LTI 1.3 tool that sits between school LMSs and the AD (Authoring & Delivery) test engine.
Continuous Flow (repo ktcf-continuous-flow, Go module git.pearsonkt.com/111/111-continuous-flow) is Pearson Knowledge Technologies' automated constructed-response scorin…
COW ("Core Warehouse", also called Assessment-as-a-Service / PWS) is Pearson's assessment-data warehouse and extract platform.
LaunchPad is Pearson's OneRoster 1.2 rostering and identity-federation platform for K-12.
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…
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 Classroom (pearson-aq-school/navvy_classroom) is a K-12 classroom assessment app.
OSCAR (Online Scoring and Reporting) is where open-ended student responses get scored.
PSAES (Pearson Scan and Assessment Engineering System) is where Pearson's scanning team engineers the paper answer documents that get scanned.