PluginBench
Skill
Official
Pass
Audit score 90

setup-zoom-mcp

anthropics/knowledge-work-plugins

Plan Zoom MCP integration and decide between MCP-only or hybrid REST+MCP architecture for Claude workflows.

What is setup-zoom-mcp?

This skill helps you evaluate whether Zoom MCP (Model Context Protocol) is appropriate for your AI workflow, and if so, design a safe setup plan. Use it when planning to integrate Zoom data with Claude, choosing between MCP and REST API approaches, or architecting a hybrid solution.

  • Determine whether your use case needs deterministic automation, AI tool orchestration, or a hybrid approach
  • Identify the Zoom MCP surface and transport assumptions required
  • Define REST API responsibilities when MCP alone is insufficient
  • Assess authentication, scope, and client capability constraints
  • Produce a minimal proof-of-concept sequence for safe deployment

How to install setup-zoom-mcp

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill setup-zoom-mcp
Claude Code
Cursor
Windsurf
Cline

How to use setup-zoom-mcp

  1. 1.Run the skill with your AI workflow or MCP use case as the argument
  2. 2.Review the recommended MCP strategy and connector expectations
  3. 3.Assess whether a hybrid REST+MCP architecture is needed for your requirements
  4. 4.Evaluate the identified risks and setup notes
  5. 5.Follow the minimal proof-of-concept sequence to validate your design

Use cases

Good for
  • Planning an AI workflow that reads Zoom meeting transcripts and metadata to generate summaries or action items
  • Deciding whether to use Zoom MCP directly or combine it with REST API calls for real-time meeting control
  • Architecting a hybrid system where MCP handles data retrieval and REST handles meeting state changes
  • Evaluating connector requirements and authentication scope before implementing Zoom integration
  • Designing a proof-of-concept to validate Zoom MCP feasibility for your Claude agent
Who it's for
  • AI engineers designing workflows over Zoom data
  • Teams planning MCP integrations with Claude
  • Developers choosing between MCP and REST API approaches
  • Architects evaluating hybrid integration strategies

setup-zoom-mcp FAQ

When should I use Zoom MCP instead of the REST API?

Use Zoom MCP when you need Claude to autonomously read and reason over Zoom data (transcripts, metadata, recordings). Use REST API for deterministic operations like scheduling or state changes. Use both together in a hybrid architecture when you need both capabilities.

What are the main connector expectations?

The skill identifies authentication requirements, OAuth scope constraints, and client capability assumptions needed to safely connect Zoom to Claude through MCP.

What does a hybrid REST+MCP architecture look like?

MCP handles data retrieval and context building (transcripts, meeting info), while REST API handles deterministic actions (scheduling, updating settings). Claude coordinates between them.

What risks should I watch for?

Common risks include insufficient OAuth scopes, missing authentication setup, transport layer misconfigurations, and unclear boundaries between MCP and REST responsibilities.

Full instructions (SKILL.md)

Source of truth, from anthropics/knowledge-work-plugins.


name: setup-zoom-mcp description: Decide when Zoom MCP is the right fit and produce a safe setup plan for Claude. Use when planning AI workflows over Zoom data, deciding between MCP and REST, or defining a hybrid MCP architecture. argument-hint: "<AI workflow or MCP use case>"

/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

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

Output

  • Recommended MCP strategy
  • Connector expectations
  • Hybrid boundaries if REST is also required
  • Risks and setup notes
  • Relevant skill links

Related Skills

  • design-mcp-workflow
  • choose-zoom-approach