Skip to main content

Microsoft 365 SharePoint MCP server

Integrate SharePoint with AI agents to automate document management, list operations, site administration, and content discovery. An AI agent connected to SharePoint can upload and manage files, create and modify lists, search documents, manage permissions, apply metadata and retention policies, and generate reports—all from natural language requests. Use this for enterprise document workflows, team collaboration automation, content governance, or knowledge management.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.

Before you begin​

You'll need:

  • Access to AI Gateway with permission to create MCP servers
  • API credentials for the application you're connecting (see the relevant application page for what to collect)

Create an MCP server​

Find the API in the catalog​

  1. Sign in to AI Gateway and select MCP Servers from the left navigation.
  2. Select New MCP Server.
  3. Search for the application you want to connect, then select it from the catalog.

Configure the server​

  1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
  2. Enter a Description so your team knows what the server is for.
  3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
  4. Toggle Production mode on if this server will be used in a live workflow.
  5. Select Next.

Configure authentication​

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security​

  1. Set any Rate limits appropriate for your use case and the API's own limits.
  2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
  3. Select Next.

Deploy​

Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

Connect to an AI client​

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

Tips​

  • You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
  • If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
  • You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication​

SharePoint integration uses OAuth 2.0 authentication through Microsoft Graph. When you register an application in Azure AD, you'll receive a tenant-specific authorization endpoint (https://login.microsoftonline.com/{tenant-id}/oauth2/v2.0/authorize) and token endpoint (https://login.microsoftonline.com/{tenant-id}/oauth2/v2.0/token). You'll need these values plus your client ID and client secret to configure the MCP server. The integration requires Graph API scopes such as Sites.Read.All, Sites.ReadWrite.All, Files.ReadWrite.All, and TermStore.ReadWrite.All to access sites, document libraries, lists, and metadata.

Available tools​

These tools enable document management, list operations, site administration, search, and permission management across SharePoint.

ToolDescription
List sitesGet all accessible SharePoint sites and team sites
Get site detailsRetrieve metadata and properties for a site
List librariesGet document libraries within a site
Upload fileUpload a document to a library
Download fileRetrieve a file's contents
Delete fileRemove a document from a library
Get file metadataRetrieve file properties and custom metadata
Create listCreate a new list in a site
List itemsGet items from a list with filtering
Create list itemAdd a new item to a list
Update list itemModify an existing list item
Delete list itemRemove an item from a list
Search contentSearch across sites and libraries
Update permissionsGrant or revoke access to a file or folder
Create sharing linkGenerate a shareable link with expiration
Get versionsList version history for a document
Update metadataSet custom metadata fields on documents

Tips​

Use consistent metadata schemas across your site so the agent can reliably categorize and search documents.

Set retention policies on library roots to ensure compliance without managing individual item lifecycles.

Leverage list views to organize large datasets for the agent to query efficiently.

Filter by site type or metadata when searching across many sites to narrow results quickly.

Grant minimal permissions by default, then expand access only when needed for specific workflows.