How to integrate Microsoft teams MCP with LlamaIndex

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Microsoft teams Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Microsoft teams to LlamaIndex using the Composio tool router. By the end, you'll have a working Microsoft teams agent that can add new member to project team, schedule an online meeting for sales, list all chats i’m part of, get details for marketing team channel through natural language commands.

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

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

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 Microsoft teams
  • Connect LlamaIndex to the Microsoft teams MCP server
  • Build a Microsoft teams-powered agent using LlamaIndex
  • Interact with Microsoft teams 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 Microsoft teams MCP server, and what's possible with it?

The Microsoft Teams MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Microsoft Teams account. It provides structured and secure access to your Teams workspace, so your agent can perform actions like managing chats, sending messages, creating meetings, and organizing teams on your behalf.

  • Automated chat and message management: Let your agent retrieve, read, and summarize messages from any Teams chat, or fetch all chats you’re part of for quick updates.
  • Team and channel organization: Easily create new teams, add members, get channel details, or archive and delete teams to keep your workspace organized.
  • Scheduling online meetings: Have your agent schedule standalone Teams meetings instantly, making it simple to coordinate with colleagues or clients without manual setup.
  • Granular access to team and chat details: Fetch full information about specific teams, channels, or even individual messages with precision, enabling rich contextual workflows.
  • Seamless membership and collaboration management: Add or update members in teams with a prompt, ensuring the right people always have access to the conversations and resources they need.

Supported Tools & Triggers

Tools
Add member to teamTool to add a user to a microsoft teams team.
Archive Teams teamTool to archive a microsoft teams team.
Get all chatsRetrieves all microsoft teams chats a specified user is part of, supporting filtering, property selection, and pagination.
Get all chat messagesRetrieves all messages from a specified microsoft teams chat using the microsoft graph api, automatically handling pagination; ensure `chat id` is valid and odata expressions in `filter` or `select` are correct.
Create online meetingUse to schedule a new standalone microsoft teams online meeting, i.
Create TeamTool to create a new microsoft teams team.
Delete Teams teamTool to delete a microsoft teams team.
Get team channelTool to get a specific channel in a team.
Get chat messageTool to get a specific chat message.
Get TeamTool to get a specific team.
List message repliesTool to list replies to a channel message.
List team membersTool to list members of a microsoft teams team.
List Teams templatesTool to list available microsoft teams templates.
List usersTool to list all users in the organization.
Create a channelCreates a new 'standard', 'private', or 'shared' channel within a specified microsoft teams team.
Create ChatCreates a new chat; if a 'oneonone' chat with the specified members already exists, its details are returned, while 'group' chats are always newly created.
Get Teams messageRetrieves a specific message from a microsoft teams channel using its team, channel, and message ids.
List TeamsRetrieves microsoft teams accessible by the authenticated user, allowing filtering, property selection, and pagination.
List team channelsRetrieves channels for a specified microsoft teams team id (must be valid and for an existing team), with options to include shared channels, filter results, and select properties.
List chat messagesRetrieves messages (newest first) from an existing and accessible microsoft teams one-on-one chat, group chat, or channel thread, specified by `chat id`.
List PeopleRetrieves a list of people relevant to a specified user from microsoft graph, noting the `search` parameter is only effective if `user id` is 'me'.
Post message to Teams channelPosts a new text or html message to a specified channel in a microsoft teams team.
Send message to Teams chatSends a non-empty message (text or html) to a specified, existing microsoft teams chat; content must be valid html if `content type` is 'html'.
Reply to Teams channel messageSends a reply to an existing message, identified by `message id`, within a specific `channel id` of a given `team id` in microsoft teams.
Unarchive Teams teamTool to unarchive a microsoft teams team.
Update Teams channel messageTool to update a message in a channel.
Update Teams chat messageTool to update a specific message in a chat.
Update TeamTool to update the properties of a team.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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 Microsoft teams account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Microsoft teams

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 Microsoft teams 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 microsoft teams_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=["microsoft_teams"],
    )

    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 Microsoft teams actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Microsoft teams 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, microsoft teams)
  • 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 Microsoft teams 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 Microsoft teams 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 Microsoft teams

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Microsoft teams 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=["microsoft_teams"],
    )

    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 Microsoft teams actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Microsoft teams 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 Microsoft teams to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Microsoft teams 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 Microsoft teams MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Microsoft teams MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Microsoft teams MCP with Claude Agent SDK

Google ADK

Google ADK

Use Microsoft teams MCP with Google ADK

LangChain

LangChain

Use Microsoft teams MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Microsoft teams MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Microsoft teams MCP with Mastra AI

CrewAI

CrewAI

Use Microsoft teams MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Microsoft teams MCP?

With a standalone Microsoft teams MCP server, the agents and LLMs can only access a fixed set of Microsoft teams tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Microsoft teams 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 Microsoft teams tools.

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

Yes, absolutely. You can configure which Microsoft teams 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 Microsoft teams data and credentials are handled as safely as possible.

Used by agents from

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

Book a call↗Get started for free