Microsoft Excel MCP for AI agents

Tools your data agent reaches for on Microsoft Excel, scoped per user.

CALL ANY TOOL

List workbooks and worksheets, read and write cell ranges, get named tables, and retrieve chart metadata.

microsoftexcel_list_charts

List charts

List all charts in an Excel worksheet stored in OneDrive. Returns chart names, IDs, type, dimensions, and position. Supports OData $top for pagination.

Parameters

Name

Type

Required

Description

item_id

string

Required

OneDrive item ID of the Excel (.xlsx) file. Example: '01BYE5RZ6QN3ZWBTUFOFD3GSPGOHDJD36K'.

worksheet_id

string

Required

Worksheet name or GUID containing the charts to list. Example: 'Sheet1'.

session_id

string

Optional

Optional workbook session ID from createSession. When provided, sent as the workbook-session-id header. Example: 'cluster=SN2&session=...'.

top

integer

Optional

Maximum number of charts to return (1-1000). Defaults to server-defined page size.

microsoftexcel_get_range

Get range

microsoftexcel_list_tables

List tables

microsoftexcel_get_table

Get table

microsoftexcel_list_comments

List comments

microsoftexcel_get_worksheet

Get worksheet

microsoftexcel_list_worksheets

List worksheets

microsoftexcel_get_named_item

Get named item

microsoftexcel_list_table_rows

List table rows

microsoftexcel_get_used_range

Get used range

microsoftexcel_list_named_items

List named items

microsoftexcel_get_chart_image

Get chart image

microsoftexcel_list_pivot_tables

List pivot tables

microsoftexcel_create_chart

Create chart

microsoftexcel_list_table_columns

List table columns

microsoftexcel_create_table

Create table

microsoftexcel_update_chart

Update chart

microsoftexcel_create_session

Create session

microsoftexcel_update_range

Update range

microsoftexcel_create_worksheet

Create worksheet

microsoftexcel_update_table

Update table

microsoftexcel_add_table_row

Add table row

microsoftexcel_update_worksheet

Update worksheet

microsoftexcel_add_named_item

Add named item

microsoftexcel_sort_range

Sort range

microsoftexcel_add_table_column

Add table column

microsoftexcel_sort_table

Sort table

microsoftexcel_clear_range

Clear range

microsoftexcel_merge_range

Merge range

microsoftexcel_filter_table

Filter table

Build your Agent

Drop the toolkit in, point it at the user, and your data agent can use Microsoft Excel from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["microsoftexcel"], toolNames: ["excel_workbooks_list", "excel_worksheets_list", "excel_range_get"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["microsoftexcel"], toolNames: ["excel_workbooks_list", "excel_worksheets_list", "excel_range_get"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["microsoftexcel"], toolNames: ["excel_workbooks_list", "excel_worksheets_list", "excel_range_get"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/microsoftexcel",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Microsoft Excel.

Read & analyze

Copy the prompt

Copied

Read [range] from [sheet name] in [workbook].

Copy the prompt

Copied

Get all rows in [table name].

Copy the prompt

Copied

List all worksheets in [workbook].

Copy the prompt

Copied

Which rows in [sheet] have [column] empty?

Write & update

Copy the prompt

Copied

Update cell [A1] in [sheet] to [value].

Copy the prompt

Copied

Write [data] to range [A1:D10].

Copy the prompt

Copied

Append a row to [table]: [values].

Copy the prompt

Copied

Clear range [A2:Z100] in [sheet].

Reporting

Copy the prompt

Copied

Read the Q4 budget workbook and flag over-budget departments.

Copy the prompt

Copied

Sum column [name] in [sheet].

Copy the prompt

Copied

List workbooks updated this week.

Copy the prompt

Copied

Get chart image from [sheet].

SEE HOW AUTH WORKS

Users authorize Microsoft Excel once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Microsoft Excel

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Microsoft Excel

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Microsoft Excel

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Microsoft Excel

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other data agents and MCP connectors. Working code, live demos, fork what fits.

GTM and RevOps Teams

Deal room sync

Pulls opportunity context from Salesforce, captures key decisions from Slack, and syncs a running summary to the deal room doc in Google Drive, but only when the deal actually changed.

People Ops and HR teams

Performance review collector

Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.

People Ops and HR teams

Offer letter routing agent

Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.

Support and Ops Teams

Support ticket automation agent

Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Microsoft Excel today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Microsoft Excel as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Microsoft Excel oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Microsoft Excel?

Yes. Pass a tool name filter to listScopedTools so the data agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Microsoft Excel.

What happens when a user revokes Microsoft Excel access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent write to workbooks stored in shared SharePoint sites the user has view-only access to?

No. Write operations require the authorizing user to have edit permissions on the file. View-only access blocks all range updates. The agent inherits the exact file rights the user has in OneDrive or SharePoint.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit