OfficeAgent.NET

OfficeAgent.NET

OfficeAgent.NET lets an AI agent or a .NET application edit your own Word, PowerPoint and Excel files without breaking them:

• Fill your company's Word template: content controls, bookmarks and repeating table rows, returned as the same file with its styles, numbering, headers and comments intact.
• Build slides on your own PowerPoint template: new slides on the template's own layouts, with named shapes, tables, charts and pictures filled and the logo and fonts left alone.
• Change clauses, prices or dates as real tracked changes that Word can accept or reject.

Every change is a typed plan that is previewed first, and if any check fails nothing is written. It is built on Microsoft's Open XML SDK and runs without Office installed.

Use it from	Start with
Claude Code, Codex, Cursor or any MCP client, with no .NET installed	uvx officeagent-mcp --stdio, pointed at a folder as in Try a Word edit
Claude Desktop	the one-click bundle in Standalone downloads
A .NET application, with or without an agent	dotnet add package OfficeAgent.Word, then Getting started

What this project does

An Office Open XML file is a package of related XML parts. A small change can affect runs, styles, numbering, comments, content controls, or revision markup. OfficeAgent.NET handles that document-specific work. The model works with structured document data and JSON-serialisable operations such as "replace this clause as a tracked change" or "add a row to this table."

The same engine is available in three forms:

• an MCP server for agents that support the Model Context Protocol;
• tools for Microsoft Agent Framework and Microsoft.Extensions.AI;
• a .NET API for applications that want to control the workflow directly.

It supports Word .docx, PowerPoint .pptx, and Excel .xlsx; one client routes each document to the module that handles it. See Scope and limitations before choosing it for a workflow that depends on Office's layout or calculation engine.

What you can build

Area	Supported workflows
Word creation and editing	Create .docx files, blank or from a .docx or .dotx template; inspect and change text, paragraphs, tables, images, styles, content controls, headers, footers, notes, page setup, and document properties; replace a picture and keep its frame
Word review	Read and manage comments, preserve or resolve review state, set one revision identity per plan, and record supported edits as tracked revisions, marking only the changed words if you choose
PowerPoint creation and editing	Build decks, blank or from a .pptx or .potx template, or update them with slides on the template's own layouts, text, tables, native editable charts, images, media, notes, comments, sections, transitions, and animations
Excel inspection and editing	Inspect worksheets, tables, and bounded ranges; read cells as Excel displays them; find raw or displayed values; set cells and formulas; append table rows; manage cell notes
Report refresh	Update the numbers, tables and charts of a Word report or PowerPoint deck from an Excel workbook, through links the document keeps for next month
Translation and bulk edits	Rewrite a paragraph in another language and keep its formatting; change every match of a phrase; apply one plan to up to 100 documents
Template generation	Find the organization's templates, bind unique Word content-control tags or PowerPoint shape names, expand repeating Word table rows, and create bounded batches with one receipt per output
Word comparison	Compare supported free-body paragraph text read-only and produce a snapshot-bound native redline plan only when all other package content is unchanged
Agent and application integration	Use MCP over stdio or HTTP, Microsoft Agent Framework tools, or the direct .NET API, with SHA-256 apply receipts and host-supplied audit actors
Document access	Work with bounded filesystem roots, SharePoint, iManage Work, Google Drive, Box, Azure Blob Storage, Amazon S3, in-memory sessions, or self-contained inline content; list a connection's documents and templates

Choose a starting point

I want to...	Start here
Decide whether OfficeAgent fits my application	Library selection guide
Try a targeted Word edit	Try a Word edit
Use OfficeAgent in Claude Desktop, or run the server without .NET (from 1.2.0)	Standalone downloads
Run the server from PyPI with uvx officeagent-mcp, with no .NET installed	Install and run
Try the server and both skills as a Claude Code plugin	Claude Code plugin
Create a Word document from scratch	Create a document
Create or edit a PowerPoint deck	PowerPoint support
Inspect or edit an Excel workbook	Excel support
Connect Codex, Claude Code, Google ADK, Copilot Studio, Microsoft 365 Copilot, Microsoft Foundry, or ChatGPT	Deployment and client setup
Use OfficeAgent from C#	Getting started
Add tools to a Microsoft Agent Framework agent	Agent integration
Add tools to a Semantic Kernel agent	SemanticKernelWordEdit sample
Use OfficeAgent from Python with the OpenAI Agents SDK or LangGraph	python-openai-agents and python-langgraph samples
Give Microsoft 365 Copilot a contract redline reviewer	M365ContractReviewer sample
Host the MCP server, or keep documents in SharePoint, iManage Work, Google Drive, Box, Azure Blob Storage, or Amazon S3	MCP server and document providers
Deploy the server to Azure Container Apps	Azure deployment
Add the server to Copilot Studio as a custom connector	Copilot Studio connector
Start new documents from the organization's templates	List documents and templates and Office template locations
Add per-user hosted connection authorization	Hosted gateway reference
Add optional PDF/page-image rendering	Visual rendering
Edit documents with no storage configured	Documents with no storage
Run a tracked-review workflow	Optional word-document-review skill
Build a .NET, MCP, or Agent Framework integration	Optional officeagent-integration skill
Build a contract-review agent	ContractReview sample
Populate quote templates or compare Word documents	Template and comparison workflows
Update this month's report or deck from the new workbook	Report refresh
Translate a document and keep its formatting	Translate a document
Rename a company or update a disclaimer across a folder	Edit many documents at once
Check support, compatibility, or security policy	Support and security
Contribute	Contributing

Try a Word edit

This small workflow demonstrates that OfficeAgent can change an existing OOXML file without flattening its structure. It uses tracked changes because the result is easy to verify in Word; review is one part of the broader document operation set.

Install the exact server version documented by this release:

dotnet tool install --global OfficeAgent.Mcp --version 1.3.0

Make a folder for the agent to work in and download the sample contract into it — a fictional services agreement with a clause to change, a table, an open comment, and a pending redline:

mkdir -p ~/officeagent-documents
curl -Lo ~/officeagent-documents/services-agreement.docx \
  https://raw.githubusercontent.com/ilia-sokolov/OfficeAgent.NET/v1.3.0/samples/documents/services-agreement.docx

PowerShell:

$officeAgentDocuments = Join-Path $env:USERPROFILE "officeagent-documents"
New-Item -ItemType Directory -Force $officeAgentDocuments | Out-Null
Invoke-WebRequest `
  https://raw.githubusercontent.com/ilia-sokolov/OfficeAgent.NET/v1.3.0/samples/documents/services-agreement.docx `
  -OutFile (Join-Path $officeAgentDocuments "services-agreement.docx")

Any .docx of your own works too — the sample just gives you something with a comment and a pending revision already in it.

Register the server with Claude Code, pointed at that folder and nothing else:

claude mcp add \
  --env OfficeAgent__FileSystemConnections__0__ConnectionId=documents \
  --env OfficeAgent__FileSystemConnections__0__RootPath=$HOME/officeagent-documents \
  --transport stdio \
  officeagent -- officeagent-mcp --stdio

PowerShell:

claude mcp add `
  --env OfficeAgent__FileSystemConnections__0__ConnectionId=documents `
  --env "OfficeAgent__FileSystemConnections__0__RootPath=$officeAgentDocuments" `
  --transport stdio `
  officeagent -- officeagent-mcp --stdio

For this review-specific workflow, you can optionally install the word-document-review skill before starting the client.

Then ask:

In services-agreement.docx, change the payment terms from thirty days to forty-five days.

Expected result when the client invokes OfficeAgent correctly: apply_plan reports writeOutcome: "committed" and returns an output id, and clause 3 reads forty-five days as a tracked change you can accept or reject. Open that output in Word and verify the change. The regression test also verifies that the sample's existing table, comment, earlier payment redline, and heading remain present with their tested XML semantics. It does not claim byte-for-byte identity for every unrelated OOXML part; see the bounded preservation evidence.

If the agent did not call apply_plan, or if writeOutcome is not committed, do not report the edit as complete. For unknown or writtenNotRegistered, preserve possibleOutput and follow storage recovery instead of retrying blindly.

What else the sample is good for — reviewing comments, accepting revisions, editing the table.

Next, try creating a Word document, generating a PowerPoint deck, or using the direct .NET workflow.

If it does not work

claude mcp list shows officeagent as failed	Check RootPath is an absolute path to a directory that exists.
The agent says it cannot find the document	Use a relative name, or an absolute path that still resolves inside RootPath.
io-error on save	Close the file in Word, then check filesystem permissions and the available disk space.
outcome-unknown or registration-failed	Do not repeat the edit. Preserve possibleOutput and follow the recovery procedure to determine whether the output already exists.

Configure broader workflows

The quick start above is deliberately the smallest thing that works. Four settings extend it:

Setting	Adds
OfficeAgent__AllowCreation=true	create_document, so "draft a project brief in brief.docx" makes a new file instead of failing
OfficeAgent__FileSystemConnections__0__AllowedExtensions__0=.docx plus OfficeAgent__FileSystemConnections__0__AllowedExtensions__1=.pptx	Word and PowerPoint on one connection. Declaring this list replaces the .docx default. Set OfficeAgent__FileSystemConnections__0__DefaultChangeMode=Direct for decks, and send "mode": "Tracked" explicitly for reviewable Word edits on that mixed connection.
OfficeAgent__EphemeralConnectionId=session	Names the in-memory session connection explicitly. With no configuration at all the server already falls back to one - this is for running it alongside storage, or under a different id
OfficeAgent__AllowInlineContent=true	Tools that carry the document as base64, for a single self-contained call

Past a couple of settings, use a file instead — the same OfficeAgent section, where a list is a list:

{
  "OfficeAgent": {
    "AllowCreation": true,
    "FileSystemConnections": [
      {
        "ConnectionId": "documents",
        "RootPath": "C:\\officeagent-documents",
        "AllowedExtensions": [ ".docx", ".pptx" ],
        "DefaultChangeMode": "Direct"
      }
    ]
  }
}

The same configuration is available as samples/config/word-and-powerpoint.json. Change RootPath before using it.

claude mcp add --transport stdio officeagent -- officeagent-mcp --stdio --config ./officeagent.json

Environment variables still override the file. Windows, PowerShell, other MCP clients, HTTP hosting and SharePoint are in Deployment and client setup; every setting is listed in MCP server.

Optional guidance for Word review

skills/word-document-review teaches the review loop: read comments and pending revisions before editing, keep reviewable Word edits as redlines, use document ids for multi-step work, and recover from stable error codes. The installation guide gives complete Bash and PowerShell steps for Claude Code and Codex, including installation from a fresh machine and verification. The skill is only needed when the task requires that review discipline; document creation, ordinary direct edits, and PowerPoint workflows use the server without it.

Optional guidance for application integration

skills/officeagent-integration helps an implementation agent choose the direct .NET API first, add MCP or Microsoft Agent Framework only when needed, and run installed-package recipes for tracked editing, template population, and complete-plan comparison. The installation guide covers both skills and makes clear that a skill does not install the runtime, NuGet packages, or MCP server.

What reaches the model

The inspect and find tools return document text and structure to the model — that is how it locates an edit. Operations on a storage connection keep the package behind an opaque id. Inline tools carry the whole file as base64 on every call. Session import/export also carries the package as base64 if the agent performs those calls; a host integration can instead move the bytes outside model context. Connect storage and model providers appropriate for the data.

The standalone server ships no authentication layer for HTTP hosting; put it behind your own, or start from the authenticated HostedGateway reference. A filesystem root is a trust boundary: its ACLs must stop untrusted principals creating, renaming or replacing entries while the server runs.

.NET quick start

Install the core package and Word module:

dotnet add package OfficeAgent.Core
dotnet add package OfficeAgent.Word

After registering services and a document provider, the edit loop looks like this:

var client = services.GetRequiredService<OfficeAgentClient>();
var doc = await client.RegisterAsync("workspace", "/srv/workspace/contract.docx");

var inspect = await client.InspectAsync("workspace", doc.ItemId);
var hit = (await client.FindAsync(
    "workspace", doc.ItemId, new FindQuery("Acme Corp"))).First();

var plan = new DocumentPlan
{
    Snapshot = inspect.Snapshot,
    Revision = new RevisionMetadata { Author = "OfficeAgent Quickstart" },
    Operations = new PlanOperation[]
    {
        new ChangeTextOp
        {
            Target = hit.Anchor,
            With = "Globex Inc.",
            Mode = ChangeMode.Tracked
        }
    }
};

var preview = await client.PreviewAsync("workspace", doc.ItemId, plan);
if (preview.IsValid)
    await client.CommitAsync("workspace", doc.ItemId, plan);

Revision.Author is the name Word displays for the tracked change. It is not an authenticated actor identity. See revision identity and audit receipts.

The complete example, including service registration and reading the saved file, is in Getting started. The minimal direct-.NET sample runs against the bundled fictional contract, so it needs no MCP client, language model, or document of your own:

dotnet run --project samples/QuickEdit -- \
  samples/documents/services-agreement.docx quickedit-output.docx

Open quickedit-output.docx in Word and verify that the payment term is a tracked change while the existing revision, comment, table, and headings remain intact. QuickEdit also accepts an exact source and replacement text for your own document. Releases also attach quickedit-sample.zip, a package-backed copy that runs outside the repository against the released NuGet packages.

The repository also contains a direct IChatClient Word-editing sample and an interactive Agent Framework sample, plus a complete contract-review agent that separates model judgement from validated document writes. The TemplateBatch sample generates two quotes from one tagged template, while DocumentComparison turns covered body-paragraph differences into a reviewable Word redline. The DocumentAssembly sample combines a proposal, statement of work, and appendix into one editable package with a multi-source audit receipt. See Word document assembly for its formatting and compatibility scope. LiabilityCap changes a value in a commented table cell as a tracked change, TableRowInsertion adds a table row as a tracked change and keeps the existing comments, and PageCounter counts rendered pages with the optional rendering package.

How it works

Every edit follows the same four steps:

1. Inspect returns a structured map of the document: its outline, paragraphs, styles, content controls, tables, images, and revisions.
2. Find searches text and returns a content-verified anchor for each match.
3. Preview validates a plan against the current document and reports the proposed changes without writing.
4. Apply commits the complete plan and saves it through the configured provider.

A plan (DocumentPlan) is a typed, JSON-serialisable list of operations. An anchor records both a location and the content expected there. If the content or optional document snapshot has changed, validation fails instead of silently targeting a different location. All operations are applied to one in-memory transaction or none are; a later provider failure can still leave storage uncertain, so callers must inspect writeOutcome before retrying.

The Word module supports changes to text, paragraphs, tables, images, styles, content controls, comment threads, footnotes and endnotes, page geometry and breaks, document properties, and tracked revisions. Operations with a Word revision representation record a redline when the connection asks for one - an inserted clause, a deleted row and a restyled heading all come back as revisions a reviewer accepts or rejects, not only a replaced phrase. Image resizing is applied directly because WordprocessingML has no revision representation for drawing dimensions. The PowerPoint module implements a broad, explicitly documented set of deck operations: text, bullets, run and paragraph formatting, template slots, style copying, tables, images, text boxes, embedded video and audio, speaker notes, resolvable comments, footers and slide numbers, sections, transitions and animations, and the slide lifecycle - adding, removing, reordering and duplicating. Several slide inserts in one plan author a deck end to end, so a single call turns nothing into a finished presentation. Any verb it does not support is named rather than silently skipped. The full operation schema is documented in Document plans, and the deck specifics in PowerPoint support.

Documents are accessed through configured providers. After registration, editing calls use a (connectionId, documentId) pair instead of a storage path or credentials. The filesystem provider restricts registrations to its root; the SharePoint, iManage Work, Google Drive and Box providers use the permissions of their configured identity, and the Azure Blob Storage and Amazon S3 providers keep registrations under the connection's prefix. CreateAsync starts a new document inside a connection: the requested .docx, .pptx or .xlsx extension selects a registered blank-document factory. CreateFromTemplateAsync starts it as a copy of a template instead, and only reads the template; a .dotx, .potx or .xltx template becomes a normal .docx, .pptx or .xlsx. The engine applies an optional initial plan in memory, and then asks the provider to create and register it without overwriting an existing name.

Documentation

Guide	Covers
Documentation hub	Learning paths, package map, and the complete documentation set
Library selection guide	Supported jobs, non-goals, package choices, alternatives, and a verified direct .NET recipe
Getting started	A complete edit from service registration to reading the result
Concepts	Anchors, snapshots, plans, providers, transactions, and capabilities
C# API reference	Generated public types and members for every library package
Document plans	JSON shapes and validation rules for every operation
Document providers	Filesystem, SharePoint, iManage Work, Google Drive, Box, Azure Blob Storage, Amazon S3, listing, templates folders, save modes, and custom providers
PowerPoint support	Slide addressing, the verbs the deck module implements, and what it preserves
Template population and comparison	Creating from a template, batch binding, repeating Word rows, comparison limits, and redline generation
Report refresh	Linking a report or deck to workbook ranges and refreshing it in one call
Translation and bulk edits	Translating with formatting kept, and one plan across many documents
Agent integration	Microsoft Agent Framework and Microsoft.Extensions.AI tools
MCP server	Server configuration, transports, security notes, and tool contracts
Deployment and client setup	Codex, Claude Code, Google ADK, Microsoft Copilot clients, Microsoft Foundry, ChatGPT, containers, and Azure
Operations	Concurrency, streams, cancellation, telemetry, and production concerns
Troubleshooting	Startup, registration, validation, concurrency, and provider failures
Failure modes	Common plan errors and what to do next
Releasing	Publishing to NuGet, PyPI, the MCP Registry, and GitHub

Contributing

Bug reports, documentation fixes, new document operations, provider integrations, and focused test cases are useful contributions. If you found a problem, open an issue with the document feature involved, the operation you attempted, and the error or unexpected result. Do not attach confidential documents; a small sanitised reproduction is enough.

To work on the code, install the .NET 10 SDK, fork the repository, and run:

dotnet build OfficeAgent.NET.sln
dotnet test OfficeAgent.NET.sln

Before starting a larger change, especially one that changes public types or the JSON wire format, open an issue so the design can be discussed. See CONTRIBUTING.md for code style, tests, and pull-request expectations.

Scope and limitations

OfficeAgent.NET edits Word .docx, PowerPoint .pptx, and Excel .xlsx files; it does not automate the Office desktop applications. It does not decrypt: a file protected by a sensitivity label or a password is refused with encrypted-document. It does not start a document from a macro-enabled template or document, which is refused with macro-enabled-document.

The deck module refuses the verbs a presentation has no vocabulary for - setProperty, revision, pageSetup, insertBreak and note - per operation, rather than applying part of a plan, and refuses an explicit tracked mode on any verb that carries one. PresentationML has no redline model, so tracked changes are Word-only, and a slide has no header (that is a notes and handout concept). Animations cover the effects expressible as a filtered p:animEffect; fly-in, zoom and motion paths are refused rather than approximated. See PowerPoint support for what a deck does and does not accept.

The core engine does not render pages, calculate Word fields, or evaluate Excel formulas. Formula edits set the workbook to recalculate when Excel opens it. The optional OfficeAgent.Excel.Calculation package calculates a verified set of Excel functions and writes the results as cached values; see formula calculation. Operations that depend on pagination, table-of-contents rendering, or field recalculation are outside the core scope. Preview reports structural changes. The optional rendering package can produce PDF-derived page images through external processes, but it does not yet detect overflow or page-fit problems. Test the workflow on representative documents and keep human review in the loop for consequential edits.

Two more limits worth knowing before you build on it:

• Token savings depend on how you connect. Addressing a document by id keeps the package out of the conversation, and inspection can be narrowed with fidelity and paging - that is where the saving comes from. The inline *_content tools are the deliberate exception: they carry the whole file as base64 in both directions, which costs tokens in proportion to file size. They suit a single self-contained call, not a sequence of edits - a model asked to pass a document of a few kilobytes back for a second edit reproduces it imperfectly and the follow-up fails. Use a connection, or a session connection, when more than one edit is coming.
• Review guidance is optional. For review tasks, the server alone does not make an agent read open comments before editing or choose a redline. The word-document-review skill teaches that workflow; without it, review behaviour depends on the model and the prompt.

Commercial support

OfficeAgent.NET is MIT-licensed and can be self-hosted. Commercial support and deployment assistance are available from dotaction: contact dotaction. That service is separate from the project: it is governed by its own agreement and does not change the library's license, compatibility promise or community support policy.

Privacy Policy

OfficeAgent.NET runs on your machine or your own server and collects nothing: no telemetry, no analytics, no calls home. It reads and writes only the documents in the folders, SharePoint libraries, other document stores, or session connections it is given, and contacts no third party except the storage service of a connection a host configures: SharePoint, iManage Work, Google Drive, Box, Azure Blob Storage or Amazon S3. Tool results go to the AI assistant using it, under that assistant's own policy. The full policy, including what is stored and for how long, is in PRIVACY.md.

License

MIT. See LICENSE.