Read ScoreApp scorecards, their questions and scoring categories, and the results (leads) they collect, with each result's per-question answers.
ScoreApp ships in the w6w first-party pack. It declares 6 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.scoreappScoreApp builds quiz funnels — “scorecards” — that score a respondent as they answer and hand back a lead with a score. This app is the read side of that: list the scorecards an account owns and filter them by status, read a scorecard’s questions with their options and scoring categories, list the results (leads) a scorecard has collected, and read one result, optionally with its answers, scores, source, activity log or enriched contact data.
The vendor’s Open API is deliberately small and read-only — there is no create, update or delete of scorecards or results — so every action here is a list or a get, and each one returns the vendor’s own response envelope verbatim, links/meta pagination included. The health surface answers the three questions separately: the credential’s liveness from the API’s own 401 Unauthenticated. body, the request-rate headroom from the x-ratelimit-limit/x-ratelimit-remaining headers ScoreApp sends on every response, and the vendor’s platform status as a declared absence, since ScoreApp publishes no status page.
Three routes to the same 6 actions. The Workflow tab is generated from ScoreApp's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
result-answers-get Read one result's per-question answers, with the questions and options they answer.
result-list List a scorecard's results (leads), with filters for date, status and search.
scorecard-categories-get Read a scorecard's scoring categories, visible and hidden alike.
scorecard-list List the scorecards this account owns, with their status, key and domain.
scorecard-questions-get Read a scorecard's questions with their answer options and scoring categories.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying ScoreApp's real ids.
{
"manifestVersion": "2",
"name": "scoreapp-example",
"steps": [
{
"id": "result-answers-get",
"uses": {
"app": "io.w6w.scoreapp",
"action": "result-answers-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"scorecard": "<scorecard>",
"result": "<result>"
}
}
]
}result-answers-get result-get result-list scorecard-categories-get scorecard-list +1 more action available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for ScoreApp, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to ScoreApp. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "result-answers-get",
payload: {
scorecard: "<value>",
result: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action result-answers-get --payload '{"scorecard":"<value>","result":"<value>"}' Give an AI agent ScoreApp — without giving it ScoreApp's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.scoreapp#result-answers-get",
"input": {
"scorecard": "<scorecard>",
"result": "<result>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's ScoreApp connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
ScoreApp's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. ScoreApp itself is MIT, and the runtime that executes it is source-available (FSL).
ScoreApp declares its own checks, so its health is a property of the app rather than something the host guesses at.
x-ratelimit-limit / x-ratelimit-remaining, read off a signed GET /scorecards?limit=1 call — the same request the auth:api-key check makes. ScoreApp sends both headers on every response, including its 401s.