Setup Zoom Mcp

anthropics/knowledge-work-pluginsOfficial

If you're thinking about building AI workflows on top of Zoom data, this skill helps you figure out whether you need MCP alone, the REST API alone, or both working together. It walks through a five-step process that surfaces auth constraints, connector assumptions, and the boundaries between deterministic automation and AI orchestration. The output is a concrete setup plan with proof-of-concept steps, not just architecture diagrams. Honestly, this is most useful when you're in that messy planning phase where you know you want Claude to work with Zoom recordings or meeting data but haven't nailed down the technical approach yet.

skills.sh installs: 2.1K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill setup-zoom-mcp --agent claude-code

Installs into .claude/skills of the current project.

Files

/setup-zoom-mcp

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Plan a Zoom MCP workflow and decide when to use MCP alone versus a hybrid REST API + MCP architecture.

Usage

/setup-zoom-mcp $ARGUMENTS

Workflow

Determine whether the goal is deterministic automation, AI tool orchestration, or a hybrid.
If MCP is appropriate, identify the likely Zoom MCP surface and transport assumptions.
If MCP alone is not enough, define the REST API responsibilities separately.
Call out auth, scope, and client capability constraints.
End with a minimal proof-of-concept sequence.