How to integrate Share point MCP with LlamaIndex

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

30 min · no commitment · see it on your stack

Share point logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Share point to LlamaIndex using the Composio tool router. By the end, you'll have a working Share point agent that can create a new project folder in sharepoint, add a task item to the marketing list, find if john doe exists as a sharepoint user through natural language commands.

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

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

Also integrate Share point 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 Share point
  • Connect LlamaIndex to the Share point MCP server
  • Build a Share point-powered agent using LlamaIndex
  • Interact with Share point 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 Share point MCP server, and what's possible with it?

The Share point MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your SharePoint account. It provides structured and secure access to your SharePoint sites, so your agent can create folders, manage lists, handle users, and organize your team's content with ease.

  • Automated folder creation and organization: Instruct your agent to create new folders in SharePoint to keep your documents neatly organized by project, department, or workflow.
  • List and item management: Let your agent create new SharePoint lists for tracking tasks, issues, or inventory, and add items to lists automatically as your needs evolve.
  • User provisioning and access control: Quickly create new SharePoint users or remove existing ones, helping you manage team access and collaboration securely and efficiently.
  • User lookup and verification: Have your agent search for users across Microsoft Graph and SharePoint to confirm their existence and check their status in your organization.

Supported Tools & Triggers

Tools
Add Attachment to List ItemTool to add an attachment to a SharePoint list item.
Add Field Link to Content TypeTool to add a field link to a list content type.
Add Role Assignment to List ItemTool to add a role assignment to a list item.
Add Role Assignment to SharePoint ListTool to add a role assignment to a SharePoint list.
Break Role Inheritance on List ItemTool to break permission inheritance on a list item.
Break Role Inheritance on ListBreaks permission inheritance on a SharePoint list, allowing you to set unique permissions.
Check In SharePoint FileTool to check in a file.
Create Content TypeTool to create a new content type in SharePoint.
Create Drive Item Sharing LinkTool to create a sharing link for a drive item in SharePoint or OneDrive.
Create SharePoint List FieldTool to create a new field (column) in a SharePoint list.
Create SharePoint List Item by GUIDTool to create a new item in a SharePoint list using the list's GUID.
Create List Item in FolderTool to create a list item in a specific folder within a SharePoint list.
Create SharePoint SubsiteTool to create a new SharePoint subsite under the current site.
Delete Drive Item Version ContentTool to delete content for a specific version of a drive item in SharePoint.
Delete SharePoint FolderDeletes a folder from a SharePoint document library.
Delete SharePoint ListTool to delete a SharePoint list.
Delete SharePoint List By TitleTool to delete a SharePoint list by its title.
Delete SharePoint List ItemTool to delete a SharePoint list item.
Delete Recycle Bin Item PermanentlyTool to permanently delete a SharePoint Recycle Bin item.
Download File by Server-relative URLTool to download a file by server-relative URL.
Ensure SharePoint UserEnsures a user exists in a SharePoint site by their login name.
Follow SharePoint ActorFollow a SharePoint user, document, site, or tag.
Get All SharePoint FoldersTool to retrieve all folders in the SharePoint web.
Get SharePoint List ChangesTool to retrieve changes from SharePoint list change log.
Get Content TypeTool to retrieve a single SharePoint content type by its ID.
Get Site Content TypesRetrieves all content types from the current SharePoint site.
Get Content Types for ListTool to retrieve all content types for a specific SharePoint list by GUID.
Get SharePoint Context InfoTool to retrieve SharePoint context information including the form digest value.
Get Current SharePoint UserTool to retrieve the current user for the site.
Get Drive Item AnalyticsTool to get analytics for a SharePoint drive item.
Get Group UsersRetrieves all users who are members of a specified SharePoint group.
Get Group Users By IDTool to retrieve all users in a specific SharePoint site group by group ID.
Download List Item AttachmentTool to download an attachment from a SharePoint list item.
Get SharePoint List by GUIDTool to retrieve a SharePoint list by its GUID.
Get SharePoint List By TitleTool to retrieve a SharePoint list by its title.
Get Content Type by IDTool to retrieve a specific content type from a SharePoint list by its ID.
Get List Item by IDTool to retrieve a SharePoint list item by ID.
Get SharePoint List ItemsTool to retrieve items from a SharePoint list.
Get SharePoint List Items by GUIDTool to retrieve items from a SharePoint list using its GUID.
Get List Item VersionTool to retrieve a specific version of a SharePoint list item.
Get Followed EntitiesTool to get entities the current user is following.
Get My FollowersRetrieves the list of users who are following the authenticated user in SharePoint.
Get Role DefinitionsTool to list role definitions at the web level.
Get SharePoint Site Collection InfoTool to fetch site collection metadata (URL, ID, root web URI) only—not list item or document-level details.
Get Site Drive Item by PathTool to retrieve a file or folder by its server-relative path in a SharePoint site.
Get SharePoint Site Page ContentTool to retrieve modern SharePoint Site Pages content by reading list item fields.
Get User Effective Permissions on WebGet a user's effective permissions on the current SharePoint site (Web).
Get SharePoint Webhook SubscriptionTool to retrieve a specific webhook subscription by ID from a SharePoint list.
Get SharePoint Webhook SubscriptionsTool to retrieve all webhook subscriptions on a SharePoint list.
Get SharePoint Web InfoTool to retrieve information about the current SharePoint web (site) using REST API.
Check Follow StatusTool to check if the current user is following a specified actor.
List SharePoint ListsRetrieves all lists in the current SharePoint web/site.
List Drive ChildrenTool to list children (files and folders) in a SharePoint drive using REST API v2.
List Recently Modified Drive ItemsTool to list recently modified items in a SharePoint drive using Microsoft Graph API.
List Drives via SharePoint REST APITool to retrieve drives using SharePoint REST API v2.
List Files in FolderTool to list files within a SharePoint folder (non-recursive; does not enumerate subfolders).
List Item AttachmentsTool to list all attachments for a SharePoint list item.
List SharePoint List ColumnsTool to list all column definitions in a SharePoint list.
List Recycle Bin ItemsTool to list items in the SharePoint Recycle Bin.
List Site GroupsTool to list SharePoint site groups for a site collection.
List SharePoint SitesTool to retrieve all SharePoint sites accessible to the user.
List Site UsersTool to list users in the site collection.
List Subfolders in FolderTool to list immediate child folders within a SharePoint folder.
Log SharePoint EventLog custom usage analytics events in SharePoint for tracking user activities.
Recycle SharePoint FileTool to move a file to the Recycle Bin.
Recycle SharePoint List ItemTool to move a list item to the Recycle Bin.
Rename SharePoint FolderRenames a SharePoint folder by updating its list item metadata.
Render List Data As StreamRetrieve list items from SharePoint with rich metadata and formatting.
Restore Drive Item VersionTool to restore a previous version of a SharePoint drive item.
Restore Recycle Bin ItemTool to restore a SharePoint Recycle Bin item.
Search SharePoint SiteSearch SharePoint content using Keyword Query Language (KQL).
Search SuggestTool to get search query suggestions.
Check Out SharePoint FileTool to check out a file in a document library.
Create SharePoint FolderCreates a new folder in SharePoint using the REST API.
Create SharePoint ListCreates a new list in SharePoint using the REST API.
Create SharePoint List ItemCreates a new item in a SharePoint list.
Find SharePoint UserSearches for a user in the SharePoint site by email address and returns their profile information if found.
Remove SharePoint UserRemoves a user from SharePoint.
Undo SharePoint File CheckoutTool to undo a file checkout, discarding any changes made while checked out.
Update SharePoint Content TypeTool to update a SharePoint content type's properties such as name, description, group, or hidden status.
Update Drive ItemTool to update the properties of a drive item (file or folder) in SharePoint using SharePoint REST API.
Update SharePoint ListTool to update properties of an existing SharePoint list.
Update SharePoint List ItemTool to update fields on an existing SharePoint list item.
Update SharePoint SiteTool to update properties of the current SharePoint site (web).
Upload File to FolderTool to upload a file to a SharePoint document library or folder.
Upload File from URL to SharePointTool to fetch a file from a URL and upload it to SharePoint.

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 Share point account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Share point

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 Share point 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 share point_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=["share_point"],
    )

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

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Share point 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=["share_point"],
    )

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

ChatGPT logo

ChatGPT

Use Share point MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Share point MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Share point MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Share point MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Share point MCP with Claude Cowork

Codex logo

Codex

Use Share point MCP with Codex

Cursor logo

Cursor

Use Share point MCP with Cursor

OpenClaw logo

OpenClaw

Use Share point MCP with OpenClaw

Hermes logo

Hermes

Use Share point MCP with Hermes

CLI logo

CLI

Use Share point MCP with CLI

Google ADK logo

Google ADK

Use Share point MCP with Google ADK

LangChain logo

LangChain

Use Share point MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Share point MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Share point MCP with Mastra AI

CrewAI logo

CrewAI

Use Share point MCP with CrewAI

OpenCode logo

OpenCode

Use Share point MCP with OpenCode

VS Code logo

VS Code

Use Share point MCP with VS Code

FAQ

What are the differences in Tool Router MCP and Share point MCP?

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

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

Yes, absolutely. You can configure which Share point 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 Share point 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↗