HubSpot Service Hub MCP server
Create a powerful Model Context Protocol (MCP) server for HubSpot Service Hub to automate support ticket management, customer communication, knowledge base operations, and service analytics. This integration enables AI agents to handle help desk automation, customer self-service, satisfaction tracking, and team collaboration with enterprise-grade security.
Setting up an MCP server
This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the Authentication section on this page.
Before you begin
You'll need:
- Access to AI Gateway with permission to create MCP servers.
- API credentials for the application you're connecting (see the Authentication section on this page for what to collect).
Create an MCP server
Find the app in the catalog
- Sign in to AI Gateway and select App Catalog from the left navigation.
- Search for the application you want to connect, then select it from the catalog.
- Select Create MCP Server to start the wizard.
App Configuration
Confirm the Base URL for the API, then, under Tools, select the endpoints you want to expose. Select Next.
MCP Server Setup
- Enter a Name for your server — something descriptive that identifies both the application and its purpose.
- Enter a Description so your team knows what the server is for.
- Set the log level: choose Production Mode for terser logs, or Non-Production Mode for more verbose logs that can help with debugging.
- Select Next.
Authentication
Enter the authentication details for the application. This varies by service — see the Authentication section on this page for the specific credentials, OAuth URLs, and scopes to use.
Review
Look over the summary of your MCP server configuration, then select Create & Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.
Connect to an AI client
Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:
Tips
- You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
- If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
Authentication
HubSpot Service Hub uses OAuth 2.0 for secure API access. Create an app in HubSpot's developer portal to obtain your Client ID and Client Secret. In HubSpot, go to Settings > Integrations > Private Apps and create a private app to get your credentials.
| Value | Setting |
|---|---|
| Auth endpoint | https://app.hubspot.com/oauth/authorize |
| Token endpoint | https://api.hubapi.com/oauth/v1/token |
| Scopes | tickets, conversations.read, conversations.write, content, crm.objects.feedback_submissions.read, crm.objects.feedback_submissions.write |
Available tools
These tools let AI agents manage the complete customer support lifecycle—from ticket creation through resolution and feedback collection. They handle triage, communication, knowledge management, and performance tracking.
| Tool | Description |
|---|---|
| List tickets | Find support tickets by status, priority, or date range |
| Create ticket | Create a new support ticket linked to a contact |
| Update ticket | Change ticket status, priority, or assignment |
| Delete ticket | Remove a ticket from the system |
| Associate ticket | Link ticket to contact, company, or deal |
| List conversations | View chat and messaging threads |
| Create conversation | Start a new support conversation |
| Update conversation | Change status or assign to agent |
| Send message | Reply to conversation or add internal notes |
| List knowledge articles | Find help articles by category or status |
| Create article | Publish a new knowledge base article |
| Update article | Edit article content or visibility |
| Delete article | Archive outdated articles |
| List feedback submissions | Find survey responses and satisfaction scores |
| Create feedback | Record customer satisfaction score and comments |
| Update feedback | Modify feedback submission details |
Tips
Create workflows that automatically triage tickets by category, assign them to the right team, and escalate unresolved tickets after a time threshold.
Build a knowledge base indexed by common issues, then direct customers to self-service articles before creating tickets. This reduces support volume.
Create workflows that monitor ticket age and trigger alerts or auto-escalation when tickets are approaching SLA deadlines.
Automatically send surveys after ticket closure to measure satisfaction, then flag low scores for quality review and coaching.
Link conversations across channels (email, chat, phone) to the same ticket so agents see the full customer history regardless of how they're contacted.
Cequence AI Gateway