Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/zoom/zoom-plugin/setup-zoom-mcpnpx skills add zoom/zoom-plugin --skill setup-zoom-mcpgit clone --depth 1 https://github.com/zoom/zoom-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zoom/zoom-plugin/setup-zoom-mcp)<a href="https://agentmods.dev/skills/zoom/zoom-plugin/setup-zoom-mcp"><img src="https://agentmods.dev/badge/skills/zoom/zoom-plugin/setup-zoom-mcp.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00046 | $0.01020 |
| Opus 5 | $0.00023 | $0.00510 |
| Sonnet 5 | $0.00009 | $0.00204 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
setup-zoom-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/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.
- Identify whether the client uses Claude's published connector or requires a manually registered General App.
- For manual registration, select the default, Meetings, Canvas, Chat, Tasks, Revenue Accelerator, or Whiteboard MCP template through setup-zoom-marketplace-app.
- 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, especially the difference between Claude Cowork and Claude Code auth paths.
- 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
Auth Rules
- Claude Cowork: use the published Zoom connector and complete OAuth in Claude's connector flow.
- Claude Code: for manual OAuth, start from the matching Marketplace MCP template, complete user-level OAuth, export
ZOOM_MCP_ACCESS_TOKEN, reconnect the plugin, then continue with this skill. - Scope requirements differ by MCP server. Use the server-specific scope sets below and the detailed tables in ../zoom-mcp/concepts/oauth-setup.md.
Current Zoom MCP Servers
Use the current server catalog for the complete tool-to-scope mapping. The production endpoints and scope families below were verified on 28 Jul 2026.
| Server | Endpoint | Scope set |
|---|---|---|
| Zoom MCP | https://mcp.zoom.us/mcp/zoom/streamable |
meeting:read:search, meeting:read:assets, ai_companion:read:search, cloud_recording:read:list_user_recordings, cloud_recording:read:content, docs:write:import, docs:read:export, hub:write:content, hub:read:content |
| Zoom Meetings MCP | https://mcp.zoom.us/mcp/meeting/streamable |
meeting:read:search, meeting:read:assets, cloud_recording:read:list_user_recordings, cloud_recording:read:content |
| Zoom Canvas MCP | https://mcp.zoom.us/mcp/canvas/streamable |
docs:read:*, docs:write:*, docs:update:*, and docs:delete:* scopes required by the selected Canvas tools |
| Zoom Chat MCP | https://mcp.zoom.us/mcp/chat/streamable |
team_chat:read:*, team_chat:write:*, and team_chat:update:* scopes required by the selected Chat tools |
| Zoom Tasks MCP | https://mcp.zoom.us/mcp/tasks/streamable |
tasks:read:*, tasks:write:*, tasks:update:*, and tasks:delete:* scopes required by the selected Tasks tools |
| Zoom Revenue Accelerator MCP | https://mcp.zoom.us/mcp/revenue_accelerator/streamable |
zra:read:* scopes required by the selected Revenue Accelerator tools |
| Zoom Whiteboard MCP | https://mcp.zoom.us/mcp/whiteboard/streamable |
whiteboard:read:*, whiteboard:write:*, whiteboard:update:*, and whiteboard:delete:* scopes required by the selected Whiteboard tools |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 67 lines · 46 tokens per session scan A 3aaa98810675
setup-zoom-mcp is a skill published in the GitHub repository zoom/zoom-plugin (7 stars, last pushed 29d ago), licensed MIT. It adds 46 tokens to every session and 1,020 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…