HighLevel MCP server for AI agents

Live

OAUTH 2.0

CRM AND MARKETING

CRM & Sales

HighLevel gives your agent CRM and marketing operations in each user's HighLevel sub-accounts: manage contacts and opportunities, book appointments, send messages across channels, enroll contacts in workflows and campaigns, and read invoices and payments.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
HighLevel
agent · Acme Q3
Run
What appointments are booked on the Demo calendar tomorrow?
S
highlevel_calendar_events_list
121ms
Sales agent
4 demos are booked on the Demo calendar tomorrow. The first starts at 9:30 with a contact from Northwind.
Sources: HighLevel calendar, 4 appointments
highlevel
4 appointments
18:29
Message Claude...

Tools your sales agent reaches for on HighLevel, scoped per user.

CALL ANY TOOL
102 tools for CRM and marketing in HighLevel: manage contacts, notes, and tasks, book appointments, move opportunities, send SMS and email, enroll contacts in workflows and campaigns, and read payments.
highlevel_appointment_create
Create appointment
Book an appointment for a contact on a calendar. Returns the created appointment with its ID. Use after Get Calendar Free Slots to book a time. Use Update Appointment to reschedule or change status.
Parameters
Name
Type
Required
Description
calendar_id
string
Required
ID of the calendar to book on. Get it with List Calendars. Example: CVokAlI8fgw4WYWoCtQz.
contact_id
string
Required
ID of the contact the appointment is for. Example: 0007BWpSzSwfiuSl0tR2.
location_id
string
Required
ID of the HighLevel sub-account (formerly called a location) to work in. The connected account is installed on one sub-account; use that sub-account's ID, shown in the HighLevel URL after /location/. Example: ve9EPM428h8vShlRW1KT.
start_time
string
Required
Start of the appointment in ISO 8601 format with offset. Example: 2025-06-23T03:30:00+05:30.
address
string
Optional
Free-text meeting address or location shown on the appointment, such as a street address or a meeting link. When set, meeting_location_type defaults to custom. Example: Zoom.
appointment_status
string
Optional
Status of the appointment. One of: new, confirmed, cancelled, showed, noshow, invalid. One of: `new`, `confirmed`, `cancelled`, `showed`, `noshow`, `invalid`.
assigned_user_id
string
Optional
ID of the HighLevel user the appointment is assigned to. Look it up with Search Users. Example: 0007BWpSzSwfiuSl0tR2.
description
string
Optional
Description or agenda for the appointment. Example: Booking a call to discuss the project.
end_time
string
Optional
End of the appointment in ISO 8601 format with offset. When left empty, the calendar's slot duration is used. Example: 2025-06-23T04:30:00+05:30.
ignore_date_range
boolean
Optional
Set to true to ignore the calendar's minimum scheduling notice and bookable date range.
ignore_free_slot_validation
boolean
Optional
Set to true to book even when the time is not a free slot on the calendar (this also skips the date range check).
meeting_location_id
string
Optional
ID of a meeting location configured on the calendar, taken from the calendar's locationConfigurations (see Get Calendar). Example: custom_0.
meeting_location_type
string
Optional
Kind of meeting location. One of: custom, zoom, gmeet, phone, address, ms_teams, google. One of: `custom`, `zoom`, `gmeet`, `phone`, `address`, `ms_teams`, `google`.
override_location_config
boolean
Optional
Set to true when you pass only meeting_location_type, or false when you pass only meeting_location_id, so HighLevel knows whether to override the calendar's location configuration.
rrule
string
Optional
Recurrence rule in iCalendar RFC 5545 RRULE format for a recurring appointment. DTSTART is not needed; occurrences are counted from start_time. Example: RRULE:FREQ=WEEKLY;COUNT=4.
title
string
Optional
Title of the appointment shown on the calendar. Example: Discovery call.
to_notify
boolean
Optional
Set to false to stop workflows and automations from running for this booking.
highlevel_appointment_get
Get appointment
highlevel_appointment_note_update
Update appointment note
highlevel_appointment_notes_list
List appointment notes
highlevel_business_create
Create business
highlevel_business_update
Update business
highlevel_calendar_get
Get calendar
highlevel_calendar_groups_list
List calendar groups
highlevel_contact_campaign_add
Add contact campaign
highlevel_contact_note_get
Get contact note
highlevel_contact_tags_remove
Remove contact tags
highlevel_contact_task_complete
Complete contact task
highlevel_contact_task_create
Create contact task
highlevel_contact_tasks_list
List contact tasks
highlevel_contact_update
Update contact
highlevel_contact_upsert
Upsert contact
highlevel_contact_workflow_add
Add contact workflow
highlevel_conversations_search
Search conversations
highlevel_forms_list
List forms
highlevel_invoice_get
Get invoice
highlevel_invoice_send
Send invoice
highlevel_location_tag_create
Create location tag
highlevel_location_tag_get
Get location tag
highlevel_location_tag_update
Update location tag
highlevel_location_templates_list
List location templates
highlevel_message_schedule_cancel
Cancel message schedule
highlevel_object_schema_get
Get object schema
highlevel_orders_list
List orders
highlevel_product_get
Get product
highlevel_subscriptions_list
List subscriptions

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// HighLevel tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["highlevel"], toolNames: [
    "highlevel_contact_duplicate_get",
    "highlevel_opportunity_create",
    "highlevel_message_send"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find Jane Lee, add her to the Sales pipeline, and text her a demo confirmation" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["highlevel"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find Jane Lee, add her to the Sales pipeline, and text her a demo confirmation" }],
  tools,
});

// Execute the tool call with the user's vaulted HighLevel OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["highlevel"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find Jane Lee, add her to the Sales pipeline, and text her a demo confirmation" }],
  tools,
});

// Tool call runs with the user's vaulted HighLevel OAuth token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["highlevel"] }, pageSize: 100,
});

const agent = new Agent({
  name: "sales_agent",
  model: "gemini-2.5-pro",
  instruction: "HighLevel tools scoped to this user",
  tools,
});

await agent.run("Find Jane Lee, add her to the Sales pipeline, and text her a demo confirmation");
Try these prompts
Copy any prompt into your agent. Each maps directly to a HighLevel tool. Click to copy, paste into your agent, done.
Contacts
Copy the prompt
Copied
Find the existing contact for jane@northwind.com.
Copy the prompt
Copied
Tag Jane Lee as webinar-attendee.
Copy the prompt
Copied
Enroll Jane Lee in the New Lead Nurture workflow.
Pipeline and calendar
Copy the prompt
Copied
Create a $3,000 opportunity for Jane Lee in the Sales pipeline.
Copy the prompt
Copied
Mark the Northwind opportunity as won.
Copy the prompt
Copied
Find open slots on the Demo calendar next Tuesday.
Messaging and payments
Copy the prompt
Copied
Text Jane Lee that her demo is confirmed for 2pm.
Copy the prompt
Copied
Send invoice INV-1042 to its contact by email.
Copy the prompt
Copied
List payment transactions from the last 7 days.
SEE HOW AUTH WORKS
Each user signs in to HighLevel once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
HighLevel
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
HighLevel
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
HighLevel
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
HighLevel
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other CRM and marketing connectors.
GTM and RevOps Teams
CRM AI agent
Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.
GTM and RevOps Teams
Outbound prospecting agent
Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.
Test other agents
See the same per-user auth pattern across other CRM and marketing connectors.
GTM
CRM AI agent
Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.
SALES
Outbound prospecting agent
Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared HighLevel token looks fine in a demo. In production every message and pipeline change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
HighLevel today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access HighLevel as the user or through a shared service account?
As the user. Each user signs in to HighLevel once, and Scalekit stores and refreshes their tokens. Messages, bookings, and pipeline changes the agent makes are attributed to that user in your audit trail, not a shared service account.
Where is the HighLevel OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in HighLevel?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example contact and calendar read tools without highlevel_message_send or highlevel_contact_tags_remove. Scalekit also enforces scope checks before every API call.
What happens when a user revokes HighLevel access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Which HighLevel sub-account does the agent work in?
Most tools act on one sub-account (formerly called a location), identified by its ID. highlevel_location_get returns that sub-account's details, and highlevel_users_search finds team members across the company or a sub-account.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""highlevel"": {
""url"": ""https://mcp.scalekit.com/highlevel"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.highlevel]
url = ""https://mcp.scalekit.com/highlevel""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""highlevel"": {
""url"": ""https://mcp.scalekit.com/highlevel"",
""type"": ""http""
}
}
}