Sign in Book a demo
Back to Tools
Communication OAuth
Build Your Agent View Zoom Documentation
zoom logo

Zoom MCP Tools for AI Agents

Let an agent find upcoming or past Zoom meetings, then read invitations, summaries, transcripts, and recording links.

Available Tools

7 tools available in this integration

Zoom.FindMeetings

Find the Zoom meeting a user means, from a phrase, a period, or a meeting id.

Zoom.GetMeetingInvitation

Retrieve the invitation note for a specific Zoom meeting.

Zoom.GetMeetingRecording

Get a past Zoom meeting's cloud recording as links that can be forwarded.

Zoom.GetMeetingSummary

Read the AI Companion meeting summary of a past Zoom meeting.

Zoom.GetMeetingTranscript

Read the transcript of a past Zoom meeting.

Zoom.ListUpcomingMeetings

List the Zoom meetings a user is scheduled to join, soonest first.

Zoom.WhoAmI

Identify the Zoom user the connection is authenticated as.

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find my planning meeting from last Tuesday and read its summary." Arcade helps it use the right Zoom actions without guessing meeting IDs, dates, or recording identifiers.

Up to 100x fewer tokens

Zoom meeting searches and upcoming-meeting reads return focused meeting details, while recordings, summaries, and transcripts are fetched only when requested. The agent avoids loading every past meeting's heavy content.

Complete the workflow end to end

Find the meeting, retrieve its invitation, read the summary, inspect the transcript, and fetch the recording links through one toolkit designed around the complete meeting follow-up task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Zoom

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Zoom, you can implement some of these policies:

Access when tools are listed for a user
  • Decide which tools an agent is allowed to see at all. A tool that is never listed cannot be called, whoever is asking.
Pre-execution before each tool call
  • Inspect the inputs a call is about to run with, and block it or send it for human approval when they fall outside what the agent should do unsupervised.
Post-execution after the tool returns
  • Deny the output of Zoom.GetMeetingRecording for meetings marked confidential, so recording links cannot reach the model or be forwarded by an agent.
  • Redact participant names, email addresses, phone numbers, and customer data from Zoom.GetMeetingTranscript results before they reach the model.
  • Strip meeting links, passcodes, and dial-in details from Zoom.GetMeetingInvitation results, so an agent cannot expose private access information.

How to use Zoom with your agent

Connect Zoom to your MCP client and give an agent authenticated access to each user's meetings. Follow the setup from authorization through your first meeting lookup.

Your questions, answered

A Zoom MCP server exposes Zoom capabilities as structured tools that an AI agent can call through the Model Context Protocol. After a user authorizes their account, the agent can find meetings and read invitations, recordings, summaries, transcripts, and account identity.

Arcade provides the Zoom MCP endpoint and adds user-level OAuth, agent-optimized actions, approval workflows, redaction, and scope controls. That gives teams one governed way to connect Zoom from supported agents and frameworks.

Arcade agents can find meetings by phrase, date range, or meeting ID; list upcoming meetings; retrieve invitations; and read cloud recordings, AI Companion summaries, and transcripts from past meetings. They can also identify the Zoom account connected to the session.

Arcade requests Zoom read permissions for the meeting information, invitations, cloud recordings, AI Companion summaries, transcripts, and account identity that your enabled workflow uses. Grant only the permissions required for the actions your agent needs.

Yes. Each user authorizes their own Zoom account through OAuth. Calls run under that user's authorization, so the agent can access only the meetings and content permitted by that user's Zoom grant.

Yes. Contextual Access policies can require human approval before a consequential Zoom call, redact fields from a response, or hide an action from the agent. The call proceeds only after the policy's conditions are satisfied.

Arcade proxies Zoom API calls and does not persist your Zoom content as part of normal tool execution. OAuth credentials are brokered and stored encrypted at rest, and the model never receives them.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works with Arcade Zoom, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes Zoom access while the user's authorization remains valid. If it is revoked, rotated, or can no longer be refreshed, calls stop until the user reconnects Zoom.

Zoom API rate limits and any account-level restrictions apply to calls made through Arcade. Zoom's current quotas determine how quickly an agent can scan meetings or retrieve recordings, summaries, and transcripts; throttled calls must be retried within those limits.

Ready to actually ship your agent?

Connect your agent to Zoom with managed OAuth, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Zoom Quickstart