Read and respond to Leads generated by Yelp users, for advertising and listing-management reseller partners.
Yelp Leads ships in the w6w first-party pack. It declares 7 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.yelp-leadsThe Yelp Leads API notifies a partner about every new interaction — a new lead, a new message, a phone-number opt-in — on the businesses it is subscribed to (Business Subscriptions API, subscription type WEBHOOK), and lets the partner read the full conversation and reply on the business’s behalf.
This app covers the whole of that surface: reading a lead’s details and its full event timeline (with cursor pagination), writing a text-message reply into an existing lead, marking a lead as replied through an out-of-Yelp channel (phone or email), marking events as read, listing the lead IDs a business has received (with time-range filtering), and reading a lead’s cost metrics.
Access to the Leads API itself is restricted to Yelp advertising and listing-management reseller partners meeting a minimum spend requirement — Yelp’s own recommendation for everyone else is its no-code Zapier integration.
Three routes to the same 7 actions. The Workflow tab is generated from Yelp Leads'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.
get-lead-events List the events (messages, attachments, other interactions) on a lead.
get-lead-ids-for-business List the Lead IDs a Yelp business has received, optionally filtered by time.
mark-lead-as-replied Mark a lead as replied through a channel outside the Leads API (phone or email).
mark-lead-event-as-read Mark a lead event, and every event before it, as read.
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 Yelp Leads's real ids.
{
"manifestVersion": "2",
"name": "yelp-leads-example",
"steps": [
{
"id": "get-lead",
"uses": {
"app": "io.w6w.yelp-leads",
"action": "get-lead",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"leadId": "<leadId>"
}
}
]
}get-lead get-lead-events get-lead-ids-for-business get-lead-metrics mark-lead-as-replied +2 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 Yelp Leads, 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 Yelp Leads. 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: "get-lead",
payload: {
leadId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action get-lead --payload '{"leadId":"<value>"}' Give an AI agent Yelp Leads — without giving it Yelp Leads'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.yelp-leads#get-lead",
"input": {
"leadId": "<leadId>"
}
}
}
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 Yelp Leads 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.
Yelp Leads'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. Yelp Leads itself is MIT, and the runtime that executes it is source-available (FSL).
Yelp Leads declares its own checks, so its health is a property of the app rather than something the host guesses at.