Manage leads, customers, policies, tasks and pipelines in AgencyZoom, the insurance agency management CRM.
AgencyZoom ships in the w6w first-party pack. It declares 23 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.agencyzoomAgencyZoom is a CRM built specifically for insurance agencies: leads move through sales pipelines, sold leads become customers, customers hold policies, and tasks (calls, emails, meetings, to-dos) drive the day-to-day follow-up.
This app covers that core loop — search and create leads, move a lead through its pipeline stage or mark it sold, look up and create customers and their policies, and manage tasks — plus the reference lookups (pipelines and stages, lead sources, carriers, employees, CSRs) a workflow needs to fill in the IDs those writes require.
Every path, verb and field here was verified against AgencyZoom’s own published OpenAPI 3.0 document (app.agencyzoom.com/openapi/agencyzoom.yaml) plus live probes against api.agencyzoom.com. AgencyZoom authenticates like a human user logging into the product — a username and password exchanged once for a JWT — rather than an API key, so see auth/login.ts for what that means for a workflow connection.
Three routes to the same 23 actions. The Workflow tab is generated from AgencyZoom'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.
carrier-list List the insurance carriers configured for this agency, for use with opportunity/policy carrierId.
customer-get Fetch a customer's full detail, including policies, notes, tasks and files.
customer-list Search customers by name, contact info, location, source or policy number.
customer-policy-list List the policies written for a customer (not AMS-synced policies).
lead-source-list List the lead sources configured for this agency, for use with lead-create/lead-update's required leadSourceId.
lead-update Replace a personal lead's data. Any field left blank is CLEARED, not left unchanged — fetch the lead first and pass its full data back if you only mean to change one field.
pipeline-stage-list List pipelines with their stages nested, for finding a stage ID within its pipeline.
policy-update-status Change a policy's status (cancelled, active, renewed, reinstated, rewritten).
task-list Search tasks by status, assignee, type, source or a predefined due-date period.
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 AgencyZoom's real ids.
{
"manifestVersion": "2",
"name": "agencyzoom-example",
"steps": [
{
"id": "customer-get",
"uses": {
"app": "io.w6w.agencyzoom",
"action": "customer-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"customerId": "<customerId>"
}
}
]
}customer-get carrier-list csr-list customer-list customer-policy-list +18 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 AgencyZoom, 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 AgencyZoom. 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: "customer-get",
payload: {
customerId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action customer-get --payload '{"customerId":"<value>"}' Give an AI agent AgencyZoom — without giving it AgencyZoom'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.agencyzoom#customer-get",
"input": {
"customerId": "<customerId>"
}
}
}
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 AgencyZoom 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.
AgencyZoom'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. AgencyZoom itself is MIT, and the runtime that executes it is source-available (FSL).
AgencyZoom declares its own checks, so its health is a property of the app rather than something the host guesses at.