Explore frequently asked questions about Zoom's Model Context Protocol server, including use cases, supported AI agents, data security, and implementation guidelines.

Frequently asked questions


**What is MCP?**

[Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction/) is an open standard that allows applications to share API context with large language models (LLMs), enabling the development of smart agents and automated workflows.

**When should I use the Zoom MCP server?**

Use the Zoom MCP server when:

- Building custom tools for AI models
- Creating data integration services
- Developing specialized AI assistants
- Extending AI capabilities with external services
- Building enterprise AI solutions
- Creating web-based AI tools (using SSE transport)
- Developing secure AI services with authentication

**Which AI agents work with Zoom's remote MCP server?**

The Zoom MCP server supports clients like Claude, Cursor, and VS Code.

**How do the Zoom APIs and the AI agent communicate?**

Communication happens securely over SSE/HTTP with no additional configuration needed on the agent side. This setup works well for IDE integrations and cloud-hosted agents. A local option using `stdio` is also available.

**How is Zoom protecting my data?**

Your data is protected in accordance with Zoom's [Terms of Service](https://www.zoom.com/en/trust/terms/) and [Privacy Policy](https://www.zoom.com/en/trust/privacy/). Learn more on our [Trust Center](https://www.zoom.com/en/trust/).

**How do I use the MCP server connection endpoint?**

- Build a custom MCP client using the [MCP SDK](https://modelcontextprotocol.io/docs/develop/build-client).
- Use an existing MCP client that supports SSE connections, such as Cursor.

**Can everyone generate their own server connection endpoint?**

No. Each instance or cluster has a shared SSE and streamable URL.
