sharepoint-excel-mcp
sharepoint-excel-mcp
MCP server that gives an AI agent read access to Excel files stored in SharePoint and OneDrive for Business, turning a permission-matrix spreadsheet into structured JSON.
Built for a QA automation flow: a test-case-writing agent reads Jira stories, each story references a permission matrix as a SharePoint link, and this server is what turns that link into data the agent can reason over — unattended, with no user sign-in.
Contents
Permissions ← read this one
Related MCP server: Excel Search MCP
Quick start
npm install
cp .env.example .env # then fill in TENANT_ID / CLIENT_ID / CLIENT_SECRET
npm run build
npm run doctor -- "<your sharepoint link>" # verify the whole chainNo Azure tenant yet? Everything below runs offline:
npm run mock # full tool flow against fixtures
npm run mock -- --wac # same, forcing the download fallback
npm run doctor -- --mock "https://contoso.sharepoint.com/:x:/s/QA/T?e=1"
npm testAzure app registration
Entra admin centre → App registrations → New registration. Name it, choose Accounts in this organizational directory only, leave the redirect URI blank — this is an app-only flow with no sign-in.
Copy the Directory (tenant) ID and Application (client) ID from the Overview page into
.env.Certificates & secrets → New client secret. Copy the secret Value immediately — not the Secret ID. It is shown once and cannot be retrieved later.
API permissions → Add a permission → Microsoft Graph → Application permissions. Add one of the permissions described below.
Grant admin consent for the directory. Without this, every Graph call fails with 403 no matter how correct the code is.
Admin consent is an external dependency. If you are not a Global Admin or Privileged Role Admin you cannot grant it yourself, and no amount of retrying will work around it. A 403 almost always means this step is outstanding.
Permissions
This is the part that decides how the server behaves, so it is worth understanding rather than copying.
The situation
Microsoft's own documentation for the Excel endpoints (worksheets, usedRange) states "Application: Not supported", and the Excel overview documents only delegated scopes.
In practice app-only access does work with tenant-wide Sites.Read.All. Under
Sites.Selected it commonly fails with:
403 — Could not obtain a WAC access tokenSo the server has two read paths and picks automatically.
Option A — Sites.Selected (default, least privilege)
Graph permission |
|
Access scope | Only sites you explicitly grant |
Excel Workbook API | Usually unavailable (WAC 403) |
Read path used | Download |
After granting admin consent, grant the app access to each site:
# Find the site ID
GET https://graph.microsoft.com/v1.0/sites/{tenant}.sharepoint.com:/sites/{siteName}
# Grant this app read access to that site
POST https://graph.microsoft.com/v1.0/sites/{siteId}/permissions
{
"roles": ["read"],
"grantedToIdentities": [
{ "application": { "id": "<CLIENT_ID>", "displayName": "sharepoint-excel-mcp" } }
]
}A WAC 403 under this option is expected and is not a misconfiguration. It means
the download fallback engaged and everything is working. npm run doctor reports it
as an informational branch, not a failure.
Option B — Sites.Read.All (workbook API available)
Graph permission |
|
Access scope | Every SharePoint site in the tenant |
Excel Workbook API | Available |
Read path used |
|
More capable and avoids downloading files, but it is a tenant-wide read grant. Your security team may reasonably refuse it.
Which to choose
Start with A. Both paths produce byte-identical output — there is a test asserting exactly that — so the only differences are latency and breadth of access. Move to B only if the download fallback proves too slow for your file sizes.
OneDrive / personal sites
Files under https://{tenant}-my.sharepoint.com/personal/... are not supported.
Sites.Selected does not reach personal OneDrive, and it resolves through a
different Graph path. Put the matrix in a SharePoint site document library.
Registering with Claude
claude mcp add sharepoint-excel \
--env TENANT_ID=<tenant-id> \
--env CLIENT_ID=<client-id> \
--env CLIENT_SECRET=<client-secret> \
-- node /absolute/path/to/share-point-mcp/dist/index.jsRun npm run build first. For development you can point at tsx src/index.ts
instead of the built output.
Tools
resolve_link(link)
Converts a link into stable driveId / itemId.
{ "driveId": "b!…", "itemId": "01…", "name": "matrix.xlsx", "webUrl": "https://…" }Call this once and reuse the IDs. Sharing links expire and get revoked; resolving one costs an extra Graph round trip on every call.
Three link shapes are accepted:
Shape | Example |
Sharing link |
|
Direct path |
|
Library view |
|
list_excel_sheets(link | driveId+itemId)
Worksheet names. Uncapped.
describe_sheet(ref, sheet?, headerRow?)
Headers, total row count, and up to 3 sample rows — no full data dump. This is the intended first call against an unfamiliar matrix: see the shape, then build a targeted filter.
get_permission_matrix(ref, sheet?, headerRow?, maxRows?, offset?, columns?, filter?)
The main tool. Uses the header row as keys.
{
"file": "matrix.xlsx", "sheet": "Permission Matrix",
"headers": ["Role", "Module", "Delete"],
"rowCount": 8, "returnedCount": 3, "offset": 0, "truncated": true,
"hint": "Showing 3 of 8 matching rows. Narrow with `filter` or `columns` first…",
"records": [ { "Role": "Admin", "Module": "Billing", "Delete": true } ]
}maxRows— default 500offset— for pagingcolumns— project to a subset; large saving on wide matricesfilter—{ column, equals? , contains? }, case-insensitive
rowCount is the number of rows matching the filter, not the sheet size.
get_cell_range(ref, sheet, range)
Raw values for an explicit A1 range like "A1:D20", for sheets whose layout does
not fit the header-row model.
Behaviour worth knowing
maxRows / offset / filter / columns are applied client-side
They bound what the agent receives, not what crosses the network. usedRange
returns the entire grid regardless, so maxRows: 10 on a 50,000-row sheet still
transfers all 50,000 rows.
This matters because the parameter names strongly imply server-side paging, and the
gap only shows up as unexplained latency on a large sheet. If you need to genuinely
bound the transfer, use get_cell_range with an explicit address — that is the
tool that actually does it.
Dates come back as Excel serial numbers
A date cell reads as 45292, not "2024-01-01". That is what Graph's usedRange
returns, and the download fallback normalizes to match so the two paths cannot be
told apart. Convert on the consuming side:
new Date(Date.UTC(1899, 11, 30) + serial * 86400000).
Dates before 1900-03-01 are off by one, because Excel reproduces a Lotus 1-2-3 bug that treats 1900 as a leap year. Not corrected — see the test that pins it.
Blank cells are empty strings
"", not null — again matching Graph. Fully blank rows are dropped entirely.
Header normalization
Real matrices have messy header rows, and both failure modes are silent:
Input | Becomes | Why |
|
| trimmed |
|
| named by its real sheet column |
|
| duplicates would otherwise overwrite |
The 25 MB download ceiling
Under the fallback path, files above MAX_DOWNLOAD_BYTES (default 25 MB) are
refused before the transfer starts. exceljs loads the whole workbook into
memory; an OOM would kill the stdio transport and surface to the agent as a
connection drop rather than a readable error.
Timeouts
30 s on Graph calls, 60 s on the download. A timeout is reported as its own error type naming the request, and is not retried — 429 and 5xx are retried up to 3 times, 403 never is.
Troubleshooting
Run the doctor first. It walks every leg and tells you which one broke:
npm run doctor -- "<your link>"1. Configuration 2. Link 3. Access token
4. Resolve to driveItem 5. Workbook API 6. usedRange
7. Download fallback → VerdictIt exits non-zero only when neither read path works.
Symptom | Meaning |
|
|
401 at step 3 | Wrong tenant/client ID, or the secret's ID was copied instead of its Value, or it expired |
403 at step 4 | Admin consent not granted, or the site not granted under |
404 at step 4 | Link revoked or expired. Confirm it opens in a browser — a revoked link and a bad share-ID encoding are indistinguishable from the response |
Yellow | Expected under |
403 at step 5 that is not yellow | A genuine consent problem, not a WAC issue |
npm run encode -- "<link>" prints the share ID and the exact Graph request to
paste into Graph Explorer —
useful for isolating an encoding problem from a permissions one.
Limitations
.xlsxonly..xlsand.csvare not supported by the Excel REST APIs.No consumer OneDrive. Business platform only.
No personal OneDrive sites (
/personal/…). Use a SharePoint site library.Read-only. No write tools, by design.
Dates are Excel serials; pre-1900-03-01 dates are off by one.
Development
npm test # 181 tests, no network
npm run typecheck # strict, includes tests and scripts
npm run lint
npm run dev # run the server from source
npm run fixtures # regenerate the .xlsx test fixtureLayout
src/
index.ts MCP server + tool registration, nothing else
config.ts env parsing, fail-fast validation
logger.ts stderr-only logger
auth.ts token acquisition, caching, single-flight
graph.ts authed fetch, retry, error mapping, redaction
links.ts pure: link classification + share-ID encoding
sharepoint.ts resolution + the two-path read
xlsx-fallback.ts download + exceljs parse + cell normalization
transform.ts pure: grid → recordsTesting approach
Pure logic (share-ID encoding, link parsing, the transform pipeline, cell
normalization) is unit tested with no network. Graph interactions run against a
routing stub and recorded fixtures. server.test.ts drives the real server through
an in-memory MCP client, which catches registration mistakes unit tests cannot see.
The most important test is cross-path equivalence: the same fixture is read via the workbook API and via the download fallback, and the results must be deeply equal. Testing each path alone cannot catch a divergence between them — and it caught a real one during development.
Nothing in npm test touches the network. Only npm run doctor talks to Azure.
Stdout is the protocol
Under StdioServerTransport, stdout carries JSON-RPC frames. A stray console.log
in src/ corrupts the stream and breaks the server with an opaque parse error on
the client. All logging goes to stderr via logger.ts, enforced by an eslint
no-console rule on src/**. Scripts under scripts/ are exempt — they are CLIs.
Available Tools
5 toolsdescribe_sheetDescribe a worksheetA
Inspect a sheet without pulling its data: returns the column headers, the total row count, and up to 3 sample rows. Call this FIRST against an unfamiliar matrix so you can build a targeted filter for get_permission_matrix instead of pulling everything.
Inputs: link, sheet, itemId, driveId, +1 more.
get_cell_rangeRead an explicit cell rangeA
Read raw values for an explicit A1 range, e.g. "A1:D20". Use when the sheet has a non-standard layout that the header-row model does not fit. Unlike get_permission_matrix, the range genuinely bounds what Graph transfers.
Inputs: range (required), sheet (required), link, itemId, +1 more.
get_permission_matrixRead a permission matrixA
Read a worksheet as structured records, using the header row as keys. Note that maxRows/offset/filter/columns are applied AFTER the full sheet is fetched: they bound what you receive, not what is transferred. If the result is truncated, narrow it with filter or columns first, and only page with offset as a fallback.
Inputs: link, sheet, filter, itemId, +5 more.
list_excel_sheetsList worksheetsA
List the worksheet names in a SharePoint-hosted Excel workbook.
Inputs: link, itemId, driveId.
resolve_linkResolve a SharePoint linkA
Convert a SharePoint sharing link or document URL into stable driveId/itemId values. Call this once and reuse the IDs: sharing links can expire or be revoked, and resolving them costs an extra Graph round trip on every call.
Inputs: link (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool addresses a distinct step in the workflow: resolve_link handles link-to-ID conversion, list_excel_sheets discovers sheets, describe_sheet inspects structure, get_permission_matrix reads structured data, and get_cell_range reads raw ranges. No two tools perform the same function.
All tool names follow the verb_noun snake_case pattern (resolve_link, list_excel_sheets, describe_sheet, get_permission_matrix, get_cell_range). The verbs clearly indicate the action, and naming is uniformly consistent.
Five tools is a well-scoped count for a focused Excel-reading server. Each tool covers a necessary operation without unnecessary bloat, and the set feels neither too thin nor too heavy.
The core read workflow is well-covered: resolving a link, listing sheets, inspecting structure, and reading data either as structured records or raw ranges. Minor gaps exist such as no write/update tools or a way to enumerate workbooks without a URL, but these appear outside the intended scope.
Maintenance
Related MCP Connectors
The Excel engine for AI agents: read, check and edit Excel models over MCP.
Convert, create and edit Word, PowerPoint, Excel and PDF documents from any AI agent.
Find and run governed Excel model capabilities that your organisation has published for AI agents.
Every spreadsheet is a table: Excel, CSV, Parquet and JSON as SQL tables for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to create, read, and manipulate Excel files without requiring Microsoft Excel installation. Supports comprehensive spreadsheet operations including formulas, formatting, charts, pivot tables, and data validation.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI models to search, read, and analyze Excel files from your local file system with support for multiple worksheets, text search, and JSON data conversion.4MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to create, read, and modify Excel workbooks without requiring Microsoft Excel, supporting operations like formulas, charts, pivot tables, formatting, and data validation.MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to perform Excel file operations (create, read, write, format) without requiring Microsoft Excel installation.175MIT