add_sheet
Add a new sheet to an existing Excel file
LABSCO SUMMARY
Spreadsheet work end to end in one server: read the file, run the analysis, write the workbook back.
Most spreadsheet servers stop at reading cells; this one carries through to pivot tables, DCF and variance models, and multi-sheet output with formulas intact. Two details decide whether it fits your files: the chunked reader exists for workbooks too big to return in one go, and a workspace root variable pins every read and write to a single directory when you want that boundary.
What it is
A local file server for .csv, .xlsx and .xls: reading and cell addressing at one end, statistics, pivots, financial models and multi-sheet writing at the other.
What you get
- Reading at every grain: a whole file, one A1-notation cell, a range, the header row, or a keyword search across cells
- Filtering and aggregation on a column, plus pivot tables with grouping
- Statistics per column, correlation between two numeric columns, and a profiling report across all columns
- Financial models on your own data: DCF valuation, budget versus actual variance, ratio analysis, what-if scenarios and trend analysis with growth rates and seasonality
- Writing back out: new files, extra sheets, multi-sheet workbooks with formulas and inter-sheet references, cell formatting and column auto-fit
- Cleanup passes — duplicate detection, batch data cleaning, and a VLOOKUP helper with fuzzy matching across two files
- Work spanning several files at once: aggregate or filter across a list of them, and cross-validate referential integrity between them
- Chunked reads with a sizing check first, for files too large to return in one response
Requirements
No account. Installed from npm as excel-csv-mcp-server and run over stdio as a local process with your own user's permissions. The AI-backed formula tools want one provider key — ANTHROPIC_API_KEY, OPENAI_API_KEY, DEEPSEEK_API_KEY or GEMINI_API_KEY — and fall back to a local provider that makes no network calls when none is set. Setting EXCEL_MCP_WORKSPACE_ROOT confines every read and write to one directory.
Setup effort
One command — npm install -g excel-csv-mcp-server
USE CASES
01
Understanding a spreadsheet you were just handed
Check the file size and headers, then profile every column before deciding what to ask.
02
Answering a numbers question without writing a formula
Filter the rows that qualify, aggregate the column you care about, and pivot when the answer needs a breakdown.
03
Building a valuation or a budget review
Run DCF, budget-versus-actual variance or ratio analysis directly on the sheet, then export the result as its own file.
04
Cleaning up a messy export before anyone uses it
Find the duplicate rows, run the batch cleaner over the common data-quality problems, and check the result against a reference file.
05
Producing a finished workbook, not just an answer
Write a multi-sheet Excel file with formulas and cross-sheet references, then format the cells and fit the columns.
06
Working across a folder of files that share a layout
Aggregate or filter the same column across all of them in one call instead of opening each in turn.
35 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
aggregate
Perform aggregation operations on a column
ai_provider_status
Check status of available AI providers
auto_fit_columns
Automatically adjust column widths to fit content in Excel files
budget_variance_analysis
Analyze budget vs actual performance with variance calculations
bulk_aggregate_multi_files
Aggregate same column across multiple files in parallel
bulk_filter_multi_files
Filter data across multiple files with optional export
correlation_analysis
Calculate correlation between two numeric columns
data_cleaner
Batch data cleaning operations with intelligent detection of common data quality issues
data_profile
Generate comprehensive data profiling report for all columns
dcf_analysis
Perform Discounted Cash Flow (DCF) valuation analysis for investment evaluation
evaluate_formula
Evaluate an Excel formula with given context
explain_formula
Explain what an Excel formula does in plain English
export_analysis
Export analysis results (pivot tables, statistics, etc.) to a new file
filter_rows
Filter rows based on column values
find_duplicates
Find and manage duplicate rows in Excel/CSV files with multiple strategies
format_cells
Apply formatting to Excel cells (fonts, colors, borders, alignment)
get_cell
Get the value of a specific cell using A1 notation
get_file_info
Analyze file size and get chunking recommendations
get_headers
Get the column headers (first row) of a file
get_range
Get values from a range of cells
parse_natural_language
Convert natural language to Excel formula or command
pivot_table
Create pivot table with grouping and aggregation
ratio_analysis
Perform comprehensive financial ratio analysis with industry benchmarks
read_file
Read an entire CSV or Excel file with optional chunking for large files
read_file_chunked
Read large files in manageable chunks to avoid token limits
scenario_modeling
Perform what-if scenario analysis with multiple assumptions
search
Search for cells containing a specific value
smart_data_analysis
AI-powered analysis suggestions for your data
statistical_analysis
Perform comprehensive statistical analysis on a column
trend_analysis
Analyze time series trends, growth rates, seasonality, and forecasting for sales and performance data
validate_data_consistency
Cross-validate data integrity across related files
vlookup_helper
Intelligent VLOOKUP setup and execution with error handling and fuzzy matching
write_file
Write data to a new CSV or Excel file (supports multiple sheets for Excel)
write_multi_sheet
Create a complex Excel file with multiple sheets, formulas, and inter-sheet references
BEFORE YOU INSTALL
What to know first
Tools you get
35 tools when we connected. The documentation's opening line says 37, but its table lists 35. The five AI tools work without a key; with ANTHROPIC_API_KEY or another provider key set, they send spreadsheet content to that provider.
Requires
npx on PATH
CONTEXT COST
Moderate Standing cost
Rated by the size of the 35 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g excel-csv-mcp-serverMCP Clients
Claude Code — global npm
CLAUDE CODE — GLOBAL NPM · TERMINAL
claude mcp add excel-csv --transport stdio excel-csv-mcp-serverClaude Desktop — global npm, Cursor — global npm
JSON
{
"mcpServers": {
"excel-csv": {
"command": "excel-csv-mcp-server"
}
}
}Claude Desktop — npx, Cursor — npx
JSON
{
"mcpServers": {
"excel-csv": {
"command": "npx",
"args": [
"-y",
"excel-csv-mcp-server"
]
}
}
}Claude Desktop — from source, Cursor — from source
JSON
{
"mcpServers": {
"excel-csv": {
"command": "node",
"args": [
"<YOUR_PATH_TO_EXCEL_MCP>/dist/index.js"
]
}
}
}
