excel-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@excel-mcp Summarize the sales data in workbook.xlsx by region"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
excel-mcp
An MCP server for safe .xlsx inspection and controlled workbook writes.
Directory listing
This project is also listed in the MCP directory:
Related MCP server: formulon-mcp
Status
This is an MVP. It supports workbook inspection, sheet/schema discovery, reads, search, simple filtering and numeric aggregation, plus preview-based writes. Writes are guarded by workspace confinement, SHA-256 compare-and-swap, a per-workbook lock, backup, temporary-file save, re-open verification, atomic replacement and JSONL audit logging.
Macro-enabled workbooks, external links, charts, formatting operations and non-.xlsx files are intentionally out of scope.
Quick start from GitHub
You do not need to clone this repository. Install uv once, then configure your MCP client to run the latest version directly from GitHub.
The command is:
uvx --from git+https://github.com/Matsu132/excel-mcp.git excel-mcpThe only local setting you need is the folder containing the Excel files:
EXCEL_MCP_WORKSPACE=/Users/your-name/Documents/ExcelThis keeps Excel data on your computer. The public GitHub repository provides the server code and dependencies; it does not upload your workbooks.
Developer installation
uv syncSet the workbook directory that the server is allowed to access:
export EXCEL_MCP_WORKSPACE="/absolute/path/to/workbooks"The server accepts only .xlsx files inside this directory. Relative paths are resolved from this workspace.
Starting the server
This server uses MCP over stdio. The command to register in an MCP client is:
uvx --from git+https://github.com/Matsu132/excel-mcp.git excel-mcpFor a direct local check:
EXCEL_MCP_WORKSPACE="/absolute/path/to/workbooks" uv run excel-mcpKeep the process running when the client starts it; MCP clients normally manage the process lifecycle automatically.
Claude Desktop
Add the following entry to Claude Desktop's MCP configuration file. Replace the paths with absolute paths on your machine.
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"excel-mcp": {
"command": "uvx",
"args": ["--from", "git+https://github.com/Matsu132/excel-mcp.git", "excel-mcp"],
"env": {
"EXCEL_MCP_WORKSPACE": "/Users/your-name/Documents/Excel"
}
}
}
}Restart Claude Desktop after saving the file. The excel_* tools should then appear in the MCP tools list.
OpenAI-compatible clients
For an OpenAI application, Agent SDK, or other client that supports local MCP stdio servers, register the same command as a local MCP server:
{
"name": "excel-mcp",
"command": "uvx",
"args": ["--from", "git+https://github.com/Matsu132/excel-mcp.git", "excel-mcp"],
"env": {
"EXCEL_MCP_WORKSPACE": "/Users/your-name/Documents/Excel"
}
}The exact configuration key varies by product. Use the product's local MCP or stdio server setting and map it to command, args, and env above. If the client only supports remote MCP endpoints, this repository needs an HTTP transport deployment before it can be used directly.
Other MCP clients
Clients such as Cursor, VS Code MCP extensions, Cline, Windsurf, and MCP Inspector generally accept the same stdio definition. Use:
Command: uvx
Arguments: --from git+https://github.com/Matsu132/excel-mcp.git excel-mcp
Environment: EXCEL_MCP_WORKSPACE=/Users/your-name/Documents/ExcelFor MCP Inspector, run:
EXCEL_MCP_WORKSPACE="/absolute/path/to/workbooks" uv run mcp dev src/excel_mcp/server.pyJapanese documentation
日本語のセットアップ手順は README_JAPANESE.md を参照してください。
MCP SDK
This project uses the official MCP Python SDK v2 with MCPServer and @mcp.tool(). The default transport is stdio for local MCP clients. See the official v2 documentation for the SDK API and transport details.
Available Tools
12 toolsexcel_aggregateD
Inputs: path (required), sheet (required), column (required), operation. Returns: result
excel_filterD
Inputs: path (required), sheet (required), value (required), column (required), +1 more. Returns: result
excel_group_byD
Inputs: path (required), sheet (required), key_column (required), value_column (required). Returns: object
excel_group_by_advancedD
Inputs: path (required), sheet (required), key_column (required), value_column (required), +1 more. Returns: object
excel_inspectD
Inputs: path (required). Returns: object
excel_list_sheetsD
Inputs: path (required). Returns: result
excel_preview_writeD
Inputs: path (required), sheet (required), values (required), cell, +1 more. Returns: object
excel_readD
Inputs: path (required), sheet (required), range, max_rows. Returns: result
excel_schemaD
Inputs: path (required), sheet (required). Returns: object
excel_searchD
Inputs: path (required), query (required), sheet. Returns: result
excel_write_cellD
Inputs: preview_id (required). Returns: object
excel_write_rangeD
Inputs: preview_id (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Most tools have clearly distinct purposes: reading, writing, searching, filtering, aggregating, and listing sheets. The only potential ambiguity is between excel_group_by and excel_group_by_advanced, and excel_inspect versus excel_schema, but their names suggest one is basic vs advanced and one is file-level vs structure-level, so agents can differentiate.
All tools follow a consistent excel_<action> pattern using snake_case, making the naming scheme highly predictable. Even though some are verbs (read, write) and some are nouns (schema, group_by), the uniform prefix and casing create a clear, uniform convention.
With 12 tools, the set is well-scoped for an Excel MCP server. Each tool addresses a distinct aspect of spreadsheet interaction—from inspection and reading to writing and data transformation—without being excessive or sparse.
The tool set covers core Excel operations: listing sheets, reading data, writing cells/ranges, inspecting structure, and performing search, filter, aggregate, and group-by operations. It lacks workbook-level creation/deletion or sheet management, but for data analysis and manipulation tasks, it provides a solid lifecycle without dead ends.
Maintenance
Related MCP Connectors
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
Siftable MCP server for governed work, knowledge, calendar, people, datasets, and Vault.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for reading and writing Excel (xlsx) files using SheetJS, providing tools to list sheets, read data, create files, add sheets, and update cells.510 npmMIT
- AlicenseNot gradedqualityBmaintenanceMCP server for Excel-compatible formula evaluation and workbook operations, enabling agents to open, inspect, mutate, recalculate, and save .xlsx files in-memory over stdio.99 npmApache 2.0
- AlicenseAqualityCmaintenanceMCP server for reading and inspecting local Excel files (.xlsx, .xlsm, .xls, .xlsb, .ods) with tools for inspecting metadata, reading ranges, and profiling structure.36 npmMIT
- AlicenseNot gradedqualityBmaintenanceA stateful MCP server for agent-based Excel workbook interaction, enabling safe reading, mutation, recalculation, verification, and automation of spreadsheets via deterministic JSON contracts.66Apache 2.0