Work with HighLevel (GoHighLevel) CRM: contacts, opportunities, pipelines, calendars, conversations and location metadata.
HighLevel ships in the w6w first-party pack. It declares 18 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.highlevelHighLevel (GoHighLevel) is a CRM and marketing platform built for agencies running multiple client sub-accounts, and this app works within one of those accounts. Manage contacts and their tags, track opportunities through pipelines, list calendars and appointments, and read and search conversations — the core of a sales and client-management workflow.
The connection resolves to a single sub-account automatically from the OAuth grant, so every action already knows which one it’s operating in without an id being passed around by hand. Sending a message and creating an appointment cover the two most common ways a workflow reaches out on HighLevel’s behalf, alongside reading custom fields and forms for context before acting.
Good for automating lead intake into a pipeline, syncing contact and opportunity data with another system, or triggering an appointment or message from an external event — the kind of client-facing follow-up an agency would otherwise do by hand across many accounts.
Three routes to the same 18 actions. The Workflow tab is generated from HighLevel'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.
create-opportunity Create a new opportunity on a pipeline, attached to a contact.
get-location Fetch a location's (sub-account's) details. Defaults to the connected location.
list-appointments List calendar events (appointments, blocked slots) in a time window. `startTime`/`endTime` are Unix epoch milliseconds.
list-contacts List contacts for the connected location. Cursor-paginated: take the last returned contact's `id` and `dateAdded`, pass them back as `startAfterId`/`startAfter` for the next page.
list-locations List sub-accounts (locations) visible to this credential. Only returns results for an Agency-level install — a Location-level install (the one this app's Auth supports) is already scoped to a single location and gets an empty/forbidden response here.
list-opportunities Search opportunities in the connected location, optionally filtered by pipeline, stage, contact, status or owner.
list-pipelines List the opportunity pipelines (and their stages) configured on the connected location.
send-message Send an outbound message (SMS, email, WhatsApp, Facebook/Instagram DM or live chat) to a contact. Creates a new conversation if the contact has none yet.
update-contact Update fields on an existing contact. Only the fields you set are changed.
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 HighLevel's real ids.
{
"manifestVersion": "2",
"name": "highlevel-example",
"steps": [
{
"id": "add-tag-to-contact",
"uses": {
"app": "io.w6w.highlevel",
"action": "add-tag-to-contact",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"contactId": "<contactId>",
"tags": "<tags>"
}
}
]
}add-tag-to-contact create-appointment create-contact create-opportunity get-contact +13 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 HighLevel, 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 HighLevel. 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: "create-contact",
payload: {
// firstName: "<value>",
// lastName: "<value>",
// email: "<value>",
// phone: "<value>",
// address1: "<value>",
// city: "<value>",
// state: "<value>",
// postalCode: "<value>",
// country: "<value>",
// companyName: "<value>",
// website: "<value>",
// source: "<value>",
// tags: "<value>",
// assignedTo: "<value>",
// additionalFields: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action create-contact --payload '{}' Give an AI agent HighLevel — without giving it HighLevel'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.highlevel#add-tag-to-contact",
"input": {
"contactId": "<contactId>",
"tags": "<tags>"
}
}
}
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 HighLevel 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.
HighLevel'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. HighLevel itself is MIT, and the runtime that executes it is source-available (FSL).
HighLevel declares its own checks, so its health is a property of the app rather than something the host guesses at.
status.gohighlevel.com incident feed. Unauthenticated and unsigned.
Daily and burst allowances remaining, read off the `X-RateLimit-*` response headers.