What do I configure for the SharePoint integration?

In Graphlit you configure the sharePoint Site, document Library, folder, and allowed Paths fields that define exactly what gets imported. Connector-backed services use the connected Microsoft account boundary; credential-backed services use the API key, URL, bucket, folder, or query settings shown in the setup flow.

SharePoint integration for Graphlit

Q: Can Graphlit ingest SharePoint?

Yes. Graphlit ingests sharePoint content through the SharePoint documents data source. The page-level capability includes sites and document libraries, folders and nested files, word, Excel, and PowerPoint files, and shared documents across the tenant, then turns that material into searchable content, citations, extracted entities, and observations for RAG and agents.

Q: Can agents deliver to SharePoint?

Yes. Graphlit exposes approved delivery to SharePoint through connected accounts and MCP-native distribution. Agents can create new documents in a SharePoint library, replace or append to existing pages, and upsert documents into a target folder, so side effects stay explicit and tied to Graphlit's distribution workflow.

Ingest

What gets ingested

Graphlit reads the selected SharePoint surfaces, converts the source material into searchable content, and keeps enough source metadata for grounded answers, retrieval, and downstream agent workflows.

SharePoint documents

Feed type: Site / SharePoint

SharePoint

Sites and document libraries

Folders and nested files

Word, Excel, and PowerPoint files

Shared documents across the tenant

Setup fields

SharePoint SiteDocument LibraryFolderAllowed PathsMaximum Files

Deliver

Deliver through SharePoint

Delivery pages show the full path from context to action: Graphlit retrieves context from SharePoint, agents reason over that context, and approved outputs are delivered through MCP tools and connected accounts.

Create or update document

Delivery path: Graphlit MCP + SharePoint

create, replace, append, upsert, delete

Create new documents in a SharePoint library

Replace or append to existing pages

Upsert documents into a target folder

Deliver to selected sites and libraries

Technical proof

Connect SharePoint

// Ingest from SharePoint
await client.createFeed({
  name: 'Knowledge Library',
  type: Types.FeedTypes.Site,
  site: {
    type: Types.FeedServiceTypes.SharePoint,
    sharePoint: {
      accountName: process.env.SHAREPOINT_ACCOUNT_NAME!,
      libraryId: process.env.SHAREPOINT_LIBRARY_ID!,
      folderId: process.env.SHAREPOINT_FOLDER_ID,
      authenticationType: Types.SharePointAuthenticationTypes.Connector,
      connector: { id: process.env.GRAPHLIT_CONNECTOR_ID! },
    },
    isRecursive: true,
    readLimit: 500,
  },
});

// Deliver to SharePoint
await client.distribute(
  {
    type: Types.DistributionServiceTypes.SharePoint,
    sharePoint: { siteId: process.env.SHAREPOINT_SITE_ID!, title: 'Brief' },
  },
  { id: process.env.GRAPHLIT_CONNECTOR_ID! },
  undefined,
  '# Brief\n\nGenerated from retrieved context.',
  Types.TextTypes.Markdown,
);

Prepare

What Graphlit prepares

The integration is not just a connector. Graphlit turns SharePoint into content that can be searched, cited, summarized, enriched with observations, and supplied to agents through the Graphlit API and MCP.

{
  "source": "SharePoint",
  "content": "SharePoint documents",
  "extracted": [
    "entities",
    "observations",
    "facts",
    "summaries"
  ],
  "citations": [
    "SharePoint source references"
  ],
  "agentContext": {
    "searchable": true,
    "groundedAnswers": true,
    "deliveryEnabled": true
  }
}

Use cases

What you can build with SharePoint

Build a SharePoint knowledge base from sites and document libraries and folders and nested files and search it alongside the rest of your Graphlit content.

Ask grounded questions over SharePoint context without forcing users to leave the tools where the work originally happened.

Extract people, organizations, projects, events, facts, and decisions from SharePoint content so agents can reason over durable context.

Let approved agents create new documents in a SharePoint library after retrieving the source context that justifies the delivery.

Need a code sample? Ask our AI assistant

SDK:

Try:or

FAQ

Common questions

Commonly paired integrations

View all

OneDrive

Cloud Storage

Microsoft Teams

Communication

Microsoft Outlook

Communication

Google Drive

Cloud Storage

Start building

Start building with SharePoint and Graphlit

Create a free Graphlit project, connect SharePoint, and turn real operational context into retrieval, knowledge graphs, and MCP-native agent workflows.

Create free account

Ingest SharePoint into Graphlit

What gets ingested

SharePoint documents

Deliver through SharePoint

Create or update document

What Graphlit prepares

What you can build with SharePoint

Common questions

Can Graphlit ingest SharePoint?

Can Graphlit ingest SharePoint?

What do I configure for the SharePoint integration?

What do I configure for the SharePoint integration?

Can agents deliver to SharePoint?

Can agents deliver to SharePoint?

Commonly paired integrations

Start building with SharePoint and Graphlit