Create & Edit Excel Spreadsheets with AI on Mac (Claude, Cursor, VS Code) — No Microsoft 365
The simplest way to let your AI assistant create, read, and edit Excel, Word, and PowerPoint files on your Mac without a Microsoft 365 subscription, an Office license, or any cloud API. Works with Claude Desktop, Cursor, VS Code, ChatGPT, and Windsurf. LMCP works with the Office files on your machine directly.
Why This Is Usually Harder Than It Should Be
Getting an AI assistant to produce a real .xlsx file — not a wall of text you have to paste into Excel yourself — usually runs into one of these:
- Copy-paste tables — the AI prints a markdown table and you reformat it into Excel by hand
- Microsoft Graph API — the “real” integration needs an Azure app, OAuth scopes, and a Microsoft 365 subscription
- Cloud upload — web tools that build spreadsheets server-side mean your data leaves your machine
- An Office license — many approaches assume Excel is installed and licensed
If you just want your AI to hand you a finished spreadsheet, document, or deck on your Mac, that's a lot of friction.
How LMCP Handles Office Files Differently
LMCP reads and writes Office files directly on your Mac — no Microsoft 365 subscription, no Graph API, no Azure app, and no cloud round-trip. It doesn't even need Microsoft Office installed: LMCP works with the file formats themselves (.xlsx, .docx, .pptx, .pdf).
Your AI assistant can create a brand-new spreadsheet, read an existing one, update specific cells, and save the result as a normal file anywhere on your filesystem — ready to open in Excel, Numbers, or Google Sheets.
What You Can Do
Through LMCP, your AI assistant can work with all the main Office formats:
- Excel — create a new
.xlsx, read data from any sheet, and write specific cells - Word — create a new
.docx, read its text, and append content to an existing document - PowerPoint — generate a
.pptxdeck from structured content and read slides back - PDF — extract text from any PDF for summarizing, searching, or converting
Everything happens locally. The files never leave your Mac, and there's no account to sign into for the documents themselves.
How to Install
Download LMCP and install it:
- Open the downloaded
.dmgfile from your Downloads folder - Drag Local MCP to your Applications folder
- Open Local MCP from your Applications folder — it appears in your menu bar
Takes about 30 seconds. Your AI clients are configured automatically.
After installation, restart your AI client so it picks up the new MCP tools:
- Claude Desktop — quit completely (Cmd+Q) and reopen
- Cursor — restart the editor
- VS Code — reload the window (Cmd+Shift+P → “Reload Window”)
- ChatGPT / Windsurf — restart the application
No Microsoft account, no Office license, no API key. LMCP works with Office files out of the box.
Example Prompts
Once connected, try these with your AI assistant:
- “Create an Excel file with my Q3 expenses: rent 2000, salaries 12000, software 800” — builds a real .xlsx you can open in Excel
- “Read budget.xlsx and tell me which months went over plan” — reads and analyzes a spreadsheet
- “Update cell B5 in forecast.xlsx to 15000” — writes a specific cell without touching the rest
- “Turn these meeting notes into a Word document and save it to my Desktop” — creates a formatted .docx
- “Make a 5-slide PowerPoint summarizing this project” — generates a .pptx deck
- “Extract the text from this PDF and summarize the key points” — reads a PDF locally
The result is a finished file on your Mac — not a block of text you have to reformat yourself.
Limitations
Because LMCP works with the file formats directly, keep these in mind:
- Content, not pixel-perfect styling — LMCP writes data, text, and structure; complex formatting (charts, conditional formatting, macros) is best added in Excel itself afterward
- Formulas vs. values — cell writes store values; if you need live formulas, ask for them explicitly or finish in Excel
- Local files — the file lives on your Mac; combine with LMCP's OneDrive tools to read or save into your synced OneDrive folder
- Large workbooks — very large spreadsheets read fastest when you target a specific sheet
Compared to Other Approaches
- Microsoft 365 + Graph API — full programmatic Office access but needs a subscription, an Azure app, and OAuth. Best for teams building a cloud Office integration.
- Copy-paste from chat — free but manual; you reformat every table and lose structure. Fine for one-off snippets, painful at scale.
- Web spreadsheet builders — convenient but your data is processed in the cloud.
- LMCP (local files) — create and edit real Office files entirely on your Mac, no subscription, no cloud. Best for individuals who want finished documents without the overhead.
Real-World Workflows
The value isn't one file — it's having your AI pull data from your other tools and turn it into a finished document.
From data to spreadsheet in one step
Read my last three months of invoices, total them by client, and create an Excel summary with one row per client.
Your AI gathers the numbers and hands you a real .xlsx — no manual entry.
Turn an email thread into a deck
Read the “Project X” email thread and create a 6-slide PowerPoint summarizing the decisions and next steps.
Because LMCP also reads your email, the AI can pull the source material and produce the deck in one pass.
Report straight into OneDrive
Pull this month's numbers, build an Excel report, and save it into my OneDrive “Reports” folder.
With LMCP's OneDrive tools, the finished file syncs to all your devices automatically.
LMCP also connects your AI assistant to email, OneDrive, Microsoft Teams, Calendar, Contacts, and local files. See the full list of guides or learn more at local-mcp.com.