Leads, notes, tasks, saved listings, showing requests and action plans in Sierra Interactive.
Sierra Interactive ships in the w6w first-party pack. It declares 27 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.sierrainteractiveSierra Interactive is a real-estate CRM and website platform: it captures leads from IDX search sites, assigns them to agents, tracks their saved searches and listings, and runs action plans (drip sequences) on them.
This app lets a workflow push and pull that data. Create or update a lead from a form, an ad or another CRM; find a lead by email; add a note or a follow-up task; record a saved listing, a request for information or a showing request; apply or stop a traditional or fully automated action plan; and read the reference lists (agents, sites, lead sources, statuses, tags, MLS regions, action plans) needed to fill those requests in correctly.
A Sierra API key is the only credential. It covers the Zapier-facing integration surface that Sierra publishes in its Swagger document.
Three routes to the same 27 actions. The Workflow tab is generated from Sierra Interactive'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.
action-plan-apply-automated Apply a fully automated action plan to a lead.
action-plan-apply-traditional Apply a traditional action plan to a lead.
action-plan-stop-automated Stop a fully automated action plan on a lead, optionally recording why.
list-fully-auto-stop-statuses List the accepted statuses when stopping a fully automated action plan.
list-fully-automated-action-plans List the fully automated action plans (ids for the apply and stop actions).
list-start-next-day-values List the accepted values for the start-next-day field of an action plan apply.
list-traditional-action-plans List the traditional action plans (ids for the apply and stop actions).
request-info Record a lead's request for information about a listing.
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 Sierra Interactive's real ids.
{
"manifestVersion": "2",
"name": "sierrainteractive-example",
"steps": [
{
"id": "action-plan-apply-automated",
"uses": {
"app": "io.w6w.sierrainteractive",
"action": "action-plan-apply-automated",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"actionPlanId": "<actionPlanId>",
"leadIdOrEmailOrPhone": "<leadIdOrEmailOrPhone>"
}
}
]
}action-plan-apply-automated action-plan-apply-traditional action-plan-stop-automated action-plan-stop-traditional lead-create +22 more actions 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 Sierra Interactive, 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 Sierra Interactive. 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: "action-plan-apply-automated",
payload: {
actionPlanId: "<value>",
leadIdOrEmailOrPhone: "<value>",
// note: "<value>",
// startNextDayIfAppliedAfter: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action action-plan-apply-automated --payload '{"actionPlanId":"<value>","leadIdOrEmailOrPhone":"<value>"}' Give an AI agent Sierra Interactive — without giving it Sierra Interactive'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.sierrainteractive#action-plan-apply-automated",
"input": {
"actionPlanId": "<actionPlanId>",
"leadIdOrEmailOrPhone": "<leadIdOrEmailOrPhone>"
}
}
}
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 Sierra Interactive 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.
Sierra Interactive'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. Sierra Interactive itself is MIT, and the runtime that executes it is source-available (FSL).
Sierra Interactive declares its own checks, so its health is a property of the app rather than something the host guesses at.
status.sierrainteractive.com (Atlassian Statuspage). Worst hosting region.
Unauthenticated GET /zapier/validateAPIKey. A 400 carrying Sierra's JSON `{"success": false, "errorMessage": …}` envelope passes: the API and its auth layer are answering.