Zuora MCP server
Use the Zuora MCP Server to connect with large language models (LLMs) and access tenant data, reporting, and operations through natural language.
The Zuora MCP Server connects Zuora with large language models (LLMs), such as Claude, through the Model Context Protocol (MCP). It enables AI-assisted analysis, reporting, and insights into your Zuora tenant data through conversational queries.
The Zuora MCP Server connects to your live Zuora data, SDKs, APIs, and supporting documentation sources, including the Developer Center and Zuora product documentation. Together, these sources give your team a unified view of Zuora as an Order-to-Revenue (OTR) platform.
The Zuora MCP Server supports the following teams by simplifying how they access and use Zuora data:
-
Financial analysis and reporting – Analyze key metrics, such as recurring revenue trends and subscription performance, by asking questions in natural language instead of manually building queries or reports.
-
Customer success – Retrieve account details, subscription status, and billing history without navigating multiple interfaces, so you can respond to customer inquiries faster.
-
Operations and system administration – Manage data, run workflows, and troubleshoot issues to reduce manual effort on routine system tasks.
-
IT and development – Accelerate integration work by generating code, exploring APIs, and getting best-practice guidance directly in your development environment.
Core capabilities
The Zuora MCP Server lets you work with your Zuora environment through conversational input. You can query data, explore APIs, and complete operational tasks without switching between multiple tools.
The Zuora MCP Server includes the following key capabilities:
-
Natural language queries – Ask questions about your Zuora data in plain language to analyze metrics, investigate issues, and identify trends without writing SQL.
-
Reporting and data access – Run reports, check their status, and retrieve results through AI-assisted interactions that use up-to-date tenant data.
-
Product knowledge access – Ask questions about Zuora functionality and get contextual answers across Billing, Revenue, CPQ, and Payments.
-
API discovery and integration support – Explore APIs, review data models, and generate integration code by using Zuora SDKs.
-
Security and governance controls – Ensure that all interactions follow your organization's access controls and approval policies.
MCP server types
Zuora offers two versions of the MCP Server: local and remote. The version you choose depends on your use case and requirements.
The following table compares the local and remote MCP Server options:
| Dimension | Local MCP Server | Remote MCP Server |
|---|---|---|
| Execution mechanism | Runs on your local machine. | Runs on the Zuora server. |
| Key operations supported | Supports the same set of operations as the remote MCP Server. | Supports the same set of operations as the local MCP Server. |
| Authentication | Uses the existing user's OAuth client credentials. | Uses OAuth 2.0 for MCP clients through OneID. |
| Permissions | Inherits the permissions tied to the user's OAuth credentials, along with the tenant-level Zuora AI permission, which supports read-only or read-write mode. | Inherits the permissions tied to the user who completes the authorization flow, along with the tenant-level Zuora AI permission, which supports read-only or read-write mode. |
| Installation and setup | Requires npm and Node.js on your local machine. | No installation required. |
| Ideal for | Developers and individual users. | Agentic workflows, MCP-to-MCP communication, and centralized deployment to large teams. |
| Multi-entity and multi-org support | Yes | Yes |
About Zuora MCP and customer responsibilities
Zuora MCP is a Model Context Protocol endpoint that allows approved third-party AI tools, such as Claude Desktop, Cursor, or custom agents, to read and write data in your Zuora tenant on your behalf. When a tenant is in Supervised mode, Zuora MCP exposes both read and write tools. Zuora enforces a per-action approval step for write actions in the Zuora AI product experience. However, Zuora cannot enforce that approval step for write actions performed through Zuora MCP because the approval flow is handled by the calling client. Many MCP clients prompt users before running a write action, but the behavior depends on the client. Customers using Zuora MCP are responsible for the following:
- Selecting MCP clients that prompt users for approval before running write actions, and confirming that approval settings are enabled.
- Reviewing custom agents and automations before connecting them to a production tenant.
- Controlling which users in the organization are allowed to connect third-party AI tools to a Zuora tenant.
- Protecting Zuora MCP credentials with the same care as any other API credential that can write to Zuora.
To keep Zuora MCP read-only for a tenant, an organization administrator can set the tenant mode to Read-Only in Zuora OneID. There is no separate setting that enables writes for the in-product Zuora AI experience while keeping Zuora MCP read-only.
Use MCP for Zuora integrations
Use Model Context Protocol (MCP) when you want to connect Zuora with external AI tools, automation platforms, or business systems.
| Scenario | Description |
|---|---|
| Access Zuora from external tools | Use MCP to access Zuora from tools such as ChatGPT, Claude, Cursor, or Windsurf. |
| Build custom workflows, automation, or agents | Use MCP to build workflows or agents with tools such as n8n, Glean, Gmail, or Slack. |
| Combine Zuora data with external systems | Use MCP to combine Zuora data with data from external systems, such as Salesforce, SAP, or NetSuite. |