Ingest OneDrive into Graphlit

Connect OneDrive to Graphlit so Microsoft 365 files and folders become searchable AI context, then let agents create or update approved documents through a connected Microsoft account.

Ingest + deliver

1 ingest surface • 1 delivery surface

Microsoft OAuth

Connected account boundary

Graphlit API

createFeed + queryContents

MCP-native

Agent context and delivery flows

Ingest

What gets ingested

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

OneDrive files

Feed type: Site / OneDrive

OneDrive
Personal and business drives
Folders and DriveItems
Word, Excel, and PowerPoint files
PDFs and uploaded documents

Setup fields

FolderAllowed PathsExcluded PathsMaximum Files

Deliver

Deliver through OneDrive

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

Create or update document

Delivery path: Graphlit MCP + OneDrive

create, replace, append, upsert, delete
Create new files in OneDrive
Generate Word documents from retrieved context
Replace or append to existing documents
Upsert into a target folder

Prepare

What Graphlit prepares

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

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

Use cases

What you can build with OneDrive

01

Build a OneDrive knowledge base from personal and business drives and folders and DriveItems and search it alongside the rest of your Graphlit content.

02

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

03

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

04

Let approved agents create new files in OneDrive after retrieving the source context that justifies the delivery.

Need a code sample? Ask our AI assistant

SDK:
Try:or

FAQ

Common questions

Start building

Start building with OneDrive and Graphlit

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

Create free account