How to integrate Zoom MCP with LlamaIndex

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Zoom logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Zoom to LlamaIndex using the Composio tool router. By the end, you'll have a working Zoom agent that can schedule a zoom meeting for tomorrow, add a registrant to your next webinar, summarize your last recorded meeting through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Zoom account through Composio's Zoom MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Zoom with

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Zoom
  • Connect LlamaIndex to the Zoom MCP server
  • Build a Zoom-powered agent using LlamaIndex
  • Interact with Zoom through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

What is the Zoom MCP server, and what's possible with it?

The Zoom MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Zoom account. It provides structured and secure access to your meetings, webinars, and usage data, so your agent can schedule meetings, register attendees, retrieve recordings, summarize sessions, and analyze participant engagement on your behalf.

  • Automated meeting scheduling and management: Instruct your agent to create new Zoom meetings, fetch details for upcoming or past meetings, and manage all your session logistics effortlessly.
  • Seamless participant and registrant registration: Have your agent add attendees or registrants to meetings and webinars, handling all required information and permissions automatically.
  • On-demand access to recordings and summaries: Let your agent retrieve meeting recordings or generate AI-powered meeting summaries, making it easy to review or share past sessions.
  • Insightful participant analytics: Ask your agent to fetch detailed lists of past meeting participants or generate daily usage reports, helping you track engagement and attendance trends.
  • Efficient recording and data cleanup: Direct your agent to delete outdated recordings or manage your Zoom storage, keeping your account streamlined and organized.

Supported Tools & Triggers

Tools
Triggers
Add a meeting registrantRegisters a participant for a Zoom meeting that has registration enabled.
Add a webinar registrantRegisters a participant for a Zoom webinar that has registration enabled.
Add project collaboratorsAdds one or more collaborators to a whiteboard project.
Add whiteboard collaboratorAdds one or more collaborators to a whiteboard.
Apply classification to whiteboardApplies or updates a classification label on a whiteboard.
Create a meetingEnable Zoom meeting creation via user-level apps with "me".
Create whiteboard projectCreates a new whiteboard project in Zoom.
Create a whiteboardCreates a new whiteboard for the authenticated user.
Create whiteboard exportCreates an export task to generate PDF exports and audit logs for specified whiteboards.
Create ZRA conversationTool to create a new conversation in Zoom Revenue Accelerator (ZRA).
Create ZRA conversation commentTool to create a comment on a Zoom Revenue Accelerator conversation.
Create ZRA CRM accountsTool to create or update CRM accounts in Zoom Revenue Accelerator (ZRA).
Create ZRA CRM contactsTool to bulk import or delete CRM contacts in Zoom Revenue Accelerator.
Create ZRA CRM dealsTool to bulk import or delete CRM deals in Zoom Revenue Accelerator (ZRA).
Bulk import ZRA CRM leadsTool to bulk import CRM leads into Zoom Revenue Accelerator (ZRA).
Create ZRA CRM settingsTool to register a new CRM API integration for Zoom Revenue Accelerator (ZRA).
Create ZRA user conversationTool to create a new conversation in Zoom Revenue Accelerator for a specific user.
Delete a meetingDelete or cancel a scheduled Zoom meeting.
Delete meeting recordingsDeletes all cloud recordings for a meeting or webinar.
Delete whiteboard projectDeletes a whiteboard project by its ID.
Remove project collaboratorRemoves a collaborator from a whiteboard project.
Delete whiteboardDeletes a whiteboard by its unique identifier.
Delete whiteboard collaboratorRemoves a collaborator from a whiteboard.
Delete ZRA conversationDeletes a ZRA (Zoom Revenue Accelerator) conversation by ID.
Delete ZRA conversation commentTool to delete a comment from a Zoom Revenue Accelerator conversation.
Delete ZRA CRM settingsDeletes CRM settings for Zoom Revenue Accelerator (ZRA).
Delete ZRA deal activitiesTool to delete activities from a Zoom Revenue Accelerator (ZRA) deal.
Download imported whiteboard fileDownloads a specific file that was imported into a whiteboard, including images, PDFs, DOCX, and other supported file formats.
Download whiteboard exportDownloads the exported whiteboard content for a completed whiteboard export task.
Download whiteboard session activityDownloads the activity archive file for a whiteboard archiving session.
Get a meetingRetrieves detailed information about a Zoom meeting by its ID.
Get a meeting summary (Paid accounts only)IMPORTANT: This action requires a PAID Zoom account (Pro, Business, or Enterprise plan).
Get a webinarAccess Zoom Webinar details requires Pro or higher plan and Webinar add-on.
Get daily usage reportThe daily report provides Zoom service usage details, like new users, meetings, participants, and minutes per day for a month, requiring a Pro plan or higher.
Get IQ conversation content analysisTool to retrieve content analysis for a Zoom IQ conversation by its ID.
Get IQ dealTool to get details of a specific deal in Zoom Revenue Accelerator (formerly Zoom IQ).
Get marketplace user appsRetrieves a paginated list of Zoom Marketplace apps installed for a specific user.
Get marketplace user entitlementsRetrieves marketplace entitlements for a specific Zoom user by ID or 'me'.
Get meeting recordingsTo download meeting recordings, use `download_url`.
Get past meeting participantsRetrieves the list of participants who attended a past (ended) Zoom meeting.
Get whiteboard projectRetrieves detailed information about a specific whiteboard project by its ID.
Get a userRetrieves detailed information about a specific Zoom user by ID, email, or 'me'.
Get a whiteboardRetrieves details about a specific whiteboard document.
Get whiteboard export statusRetrieves the status of a whiteboard export task by its task ID.
Get a whiteboard sessionRetrieves detailed information about a specific whiteboard session by its session ID.
Get ZRA conversation commentsTool to retrieve comments for a specific Zoom Revenue Accelerator (ZRA) conversation.
Get ZRA conversation interactionsRetrieves interaction details for a specific Zoom Revenue Accelerator (ZRA) conversation.
Get ZRA conversation scorecardsTool to retrieve scorecards for a specific conversation in Zoom Revenue Accelerator.
Get ZRA deal activitiesTool to retrieve activities associated with a Zoom Revenue Accelerator (ZRA) deal.
Import whiteboardInitiates an import of a whiteboard from an external source (Miro, Mural, or Visio files).
List all recordingsThis text details how to list Zoom cloud recordings for a user, notably by using "me" for user-level apps and requiring an OAuth token for access.
List archived filesLists archived meeting and webinar files within a specified date range (max 7 days).
List devicesLists devices in your Zoom account managed through Zoom Device Management (ZDM).
List marketplace app custom fieldsTool to retrieve custom fields configured for a Zoom Marketplace app.
List meetingsThis Zoom API lists a user's scheduled meetings using the `me` value for user-level apps, excluding instant meetings and only showing unexpired ones.
List meeting summary templatesTool to retrieve a list of meeting summary templates for a specified user.
List past meeting instancesTool to retrieve all UUIDs for past instances of a given meeting.
List project collaboratorsLists all collaborators for a whiteboard project, including their roles and permissions.
List whiteboard projectsLists all whiteboard projects accessible to the user.
List user collaboration devicesTool to list collaboration devices associated with a user.
Get user settingsTool to retrieve a user's settings including meeting scheduling, in-meeting features, email notifications, recording, telephony, and security preferences.
List webinar participantsGet a list of past webinar participants with a Pro plan or above plus an add-on.
List webinar registrantsRetrieves the list of registrants for a webinar with registration enabled.
List webinarsThe API lists all scheduled webinars for Zoom users with a webinar plan, using `me` for user-level apps.
List whiteboardsLists all whiteboards accessible to the user.
List ZRA conversationsTool to list all conversations in Zoom Revenue Accelerator.
List ZRA CRM accountsLists CRM accounts from Zoom Revenue Accelerator by account IDs.
List ZRA CRM contactsTool to retrieve CRM contact information from Zoom IQ Revenue Accelerator (ZRA).
List ZRA CRM dealsTool to retrieve CRM deal information from Zoom Revenue Accelerator (ZRA).
List ZRA CRM leadsTool to retrieve CRM lead information from Zoom IQ Revenue Accelerator (ZRA).
List ZRA CRM settingsTool to retrieve the current CRM API registration information for Zoom Revenue Accelerator (ZRA).
List ZRA dealsTool to list deals from Zoom Revenue Accelerator (ZRA).
List ZRA scheduled itemsTool to list scheduled Zoom Revenue Accelerator (ZRA) items.
List ZRA settings indicatorsTool to retrieve account indicator settings for Zoom Revenue Accelerator (ZRA).
List ZRA user conversation playlistsTool to list conversation playlists for a specific user in Zoom Revenue Accelerator.
Move whiteboards to projectMoves one or more whiteboards to a specified Zoom Whiteboard project.
Remove whiteboard classificationRemoves the classification label from a whiteboard.
Remove whiteboards from projectRemoves one or more whiteboards from a specified Zoom Whiteboard project.
Search company contactsTool to search company contacts in Zoom by first name, last name, or email.
Update a meetingTo update a meeting via API, ensure `start_time` is future-dated; `recurrence` is needed.
Update classification labelUpdates an existing classification label in Zoom Whiteboard.
Update a whiteboard projectUpdates the name of an existing whiteboard project in Zoom.
Update project collaboratorsUpdates collaborator permissions for a whiteboard project.
Update whiteboard collaboratorUpdates collaborator settings for a whiteboard.
Update whiteboard share settingsUpdates the sharing settings for a whiteboard, controlling who can access and edit the whiteboard.
Update ZRA conversation commentTool to update a comment in a Zoom Revenue Accelerator conversation.
Update ZRA conversation hostTool to update the host of a Zoom Revenue Accelerator (ZRA) conversation.
Upload Whiteboard FileUploads a file to be used in Zoom Whiteboard.
Validate marketplace app manifestTool to validate a Zoom Marketplace app manifest before submission or update.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Zoom account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Zoom

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Zoom access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called zoom_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["zoom"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Zoom actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Zoom actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, zoom)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Zoom tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Zoom database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Zoom

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Zoom, then start asking questions.

Complete Code

Here's the complete code to get you started with Zoom and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["zoom"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Zoom actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Zoom actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Zoom to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Zoom tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Zoom MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Zoom MCP with ChatGPT

Antigravity logo

Antigravity

Use Zoom MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Zoom MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Zoom MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Zoom MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Zoom MCP with Claude Cowork

Codex logo

Codex

Use Zoom MCP with Codex

Cursor logo

Cursor

Use Zoom MCP with Cursor

OpenClaw logo

OpenClaw

Use Zoom MCP with OpenClaw

Hermes logo

Hermes

Use Zoom MCP with Hermes

CLI logo

CLI

Use Zoom MCP with CLI

Google ADK logo

Google ADK

Use Zoom MCP with Google ADK

LangChain logo

LangChain

Use Zoom MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Zoom MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Zoom MCP with Mastra AI

CrewAI logo

CrewAI

Use Zoom MCP with CrewAI

OpenCode logo

OpenCode

Use Zoom MCP with OpenCode

VS Code logo

VS Code

Use Zoom MCP with VS Code

FAQ

What are the differences in Tool Router MCP and Zoom MCP?

With a standalone Zoom MCP server, the agents and LLMs can only access a fixed set of Zoom tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Zoom and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Zoom tools.

Can I manage the permissions and scopes for Zoom while using Tool Router?

Yes, absolutely. You can configure which Zoom scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Zoom data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗