Email and calendar
HighLevel for AI agents.
Managed auth, ready-made tools.
Find and add contacts, manage opportunities, send messages and book appointments in HighLevel on behalf of each of your users.
About HighLevel
With the HighLevel connector, your agent works in each user’s own HighLevel sub-account. It can search and add contacts, list and create opportunities, send an SMS or email, and book an appointment on a calendar, using only the tools your project allows.
HighLevel is an all-in-one CRM and marketing platform for agencies and small businesses.
Tools
What your agent can do in HighLevel.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own HighLevel connection.
-
Search contacts
Readhighlevel_search_contactsFind contacts by name, email, phone or tag.
-
Create a contact
Writehighlevel_create_contactAdd a contact with their details and tags.
-
List opportunities
Readhighlevel_list_opportunitiesList opportunities in a pipeline with their stage.
-
Create an opportunity
Writehighlevel_create_opportunityAdd an opportunity to a pipeline stage.
-
Send a message
Writehighlevel_send_messageSend an SMS or email to a contact.
-
List calendar events
Readhighlevel_list_calendar_eventsList appointments on a calendar.
-
Book an appointment
Writehighlevel_create_appointmentBook an appointment for a contact on a calendar.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in HighLevel, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read contacts and pipelines, and switch off
highlevel_send_messageso it can never text or email a contact. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example contacts and calendars but not conversations. A call outside them is refused.
Get started
Connect HighLevel
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect HighLevel
Each end user authorizes their own HighLevel account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own HighLevel account, once. const connection = await agent200 .user("user_123") .connect("highlevel"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the HighLevel tools
Name the user, the model and the tools. The model decides which HighLevel tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "Add Lena Brooks as a new lead and tag her webinar", tools: ["highlevel"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Who signs in
Each of your users, once, on HighLevel's own sign-in page. You never see or store their HighLevel password.
-
What access is requested
The scopes the connection needs, such as reading contacts, writing opportunities or sending conversation messages, listed on HighLevel's authorization screen. Users can remove the app later from their HighLevel account settings.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the HighLevel connector and how to use it.
Connector: HighLevel, through Agent200. In code: "highlevel". What it does: Find and add contacts, manage opportunities, send messages and book appointments in HighLevel on behalf of each of your users. Page: https://www.agent200.com/connectors/highlevel/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on HighLevel's own page, through the authorization link Agent200 returns. Never ask a user for a HighLevel password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: highlevel_search_contacts, highlevel_list_opportunities, highlevel_list_calendar_events. Write tools: highlevel_create_contact, highlevel_create_opportunity, highlevel_send_message, highlevel_create_appointment. Name "highlevel" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/highlevel/framework/claude/ https://www.agent200.com/connectors/highlevel/framework/chatgpt/ https://www.agent200.com/connectors/highlevel/framework/claude-code/ https://www.agent200.com/connectors/highlevel/framework/muse/ https://www.agent200.com/connectors/highlevel/framework/grok-bot/ https://www.agent200.com/connectors/highlevel/framework/openai-dots/ https://www.agent200.com/connectors/highlevel/framework/claude-duet/ https://www.agent200.com/connectors/highlevel/framework/hermes-agent/ https://www.agent200.com/connectors/highlevel/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/highlevel.md
Guides
Use HighLevel with the AI you build on.
Step-by-step setup for HighLevel with a specific model, assistant or agent framework.
-
HighLevel + Claude
How to connect HighLevel to Claude
-
HighLevel + ChatGPT
How to connect HighLevel to ChatGPT
-
HighLevel + Claude Code
How to connect HighLevel to Claude Code
-
HighLevel + Muse
How to connect HighLevel to Muse
-
HighLevel + Grok Bot
How to connect HighLevel to Grok Bot
-
HighLevel + OpenAI Dots
How to connect HighLevel to OpenAI Dots
-
HighLevel + Claude Duet
How to connect HighLevel to Claude Duet
-
HighLevel + Hermes Agent
How to connect HighLevel to Hermes Agent
-
HighLevel + OpenClaw
How to connect HighLevel to OpenClaw
FAQ
HighLevel and Agent200, answered.
Who handles the HighLevel OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for HighLevel.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's HighLevel connection, never another user's. It cannot reach anything the user or HighLevel has not authorized.
Can I limit what my agent can do in HighLevel?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.