Sbroenne MCP Server Excel Excel CLI

Excel Automation with excelcli

Preconditions

• Windows host with Microsoft Excel installed (2016+)
• Uses COM interop — does NOT work on macOS or Linux
• Install: Download excelcli.exe from https://github.com/sbroenne/mcp-server-excel/releases/latest and add to PATH

Workflow Checklist

10+ commands? Use excelcli -q batch --input commands.json — sends all commands in one process with automatic session management. See Rule 8.

Writing Data (Step 3):

• --values takes a JSON 2D array string: --values '[["Header1","Header2"],[1,2]]'
• Write one row at a time for reliability: --range-address A1:B1 --values '[["Name","Age"]]'
• Strings MUST be double-quoted in JSON: "text". Numbers are bare: 42
• Always wrap the entire JSON value in single quotes to protect special characters

CRITICAL RULES (MUST FOLLOW)

⚡ Building dashboards or bulk operations? Skip to Rule 8: Batch Mode — it eliminates per-command process overhead and auto-manages session IDs.

Rule 1: NEVER Ask Clarifying Questions

Execute commands to discover the answer instead:

You have commands to answer your own questions. USE THEM.

Rule 2: Always End With a Text Summary

NEVER end your turn with only a command execution. After completing all operations, always provide a brief text message confirming what was done. Silent command-only responses are incomplete.

Rule 3: Session Lifecycle

Creating vs Opening Files:

# NEW file - use session create
excelcli -q session create C:\path\newfile.xlsx  # Creates file + returns session ID

# EXISTING file - use session open
excelcli -q session open C:\path\existing.xlsx   # Opens file + returns session ID

CRITICAL: Use session create for new files. session open on non-existent files will fail!

CRITICAL: ALWAYS use the session ID returned by session create or session open in subsequent commands. NEVER guess or hardcode session IDs. The session ID is in the JSON output (e.g., {"sessionId":"abc123"}). Parse it and use it.

# Example: capture session ID from output, then use it
excelcli -q session create C:\path\file.xlsx     # Returns JSON with sessionId
excelcli -q range set-values --session <returned-session-id> ...
excelcli -q session close --session <returned-session-id> --save

Unclosed sessions leave Excel processes running, locking files.

Rule 4: Data Model Prerequisites

DAX operations require tables in the Data Model:

excelcli -q table add-to-data-model --session <id> --table-name Sales  # Step 1
excelcli -q datamodel create-measure --session <id> ...               # Step 2 - NOW works

Rule 5: Power Query Development Lifecycle

BEST PRACTICE: Test M code before creating permanent queries

# Step 1: Create/open a session and capture the session ID
$session = excelcli -q session create C:\path\file.xlsx | ConvertFrom-Json
$sessionId = $session.sessionId

# Step 2: Test M code without persisting (catches errors early)
excelcli -q powerquery evaluate --session $sessionId --m-code-file query.m

# Step 3: Create permanent query with validated code
excelcli -q powerquery create --session $sessionId --query-name Q1 --m-code-file query.m

# Step 4: Load data to destination
excelcli -q powerquery refresh --session $sessionId --query-name Q1

# Step 5: Close session
excelcli -q session close --session $sessionId --save

Rule 6: Report File Errors Immediately

If you see "File not found" or "Path not found" - STOP and report to user. Don't retry.

Rule 7: Use Calculation Mode for Bulk Writes

When writing many values/formulas (10+ cells), disable auto-recalc for performance:

# 1. Create/open a session and capture the session ID
$session = excelcli -q session create C:\path\file.xlsx | ConvertFrom-Json
$sessionId = $session.sessionId

# 2. Set manual mode
excelcli -q calculationmode set-mode --session $sessionId --mode manual

# 3. Write data row by row for reliability
excelcli -q range set-values --session $sessionId --sheet-name Sheet1 --range-address A1:B1 --values '[["Name","Amount"]]'
excelcli -q range set-values --session $sessionId --sheet-name Sheet1 --range-address A2:B2 --values '[["Salary",5000]]'

# 4. Recalculate once at end
excelcli -q calculationmode calculate --session $sessionId --scope workbook

# 5. Restore automatic mode
excelcli -q calculationmode set-mode --session $sessionId --mode automatic

# 6. Close session
excelcli -q session close --session $sessionId --save

Rule 8: Use Batch Mode for Bulk Operations (10+ commands)

When executing 10+ commands on the same file, use excelcli batch to send all commands in a single process launch. This avoids per-process startup overhead and terminal buffer saturation.

# Create a JSON file with all commands
@'
[
  {"command": "session.open", "args": {"filePath": "C:\\path\\file.xlsx"}},
  {"command": "range.set-values", "args": {"sheetName": "Sheet1", "rangeAddress": "A1", "values": [["Hello"]]}},
  {"command": "range.set-values", "args": {"sheetName": "Sheet1", "rangeAddress": "A2", "values": [["World"]]}},
  {"command": "session.close", "args": {"save": true}}
]
'@ | Set-Content commands.json

# Execute all commands at once
excelcli -q batch --input commands.json

Key features:

• Session auto-capture: session.open/create result sessionId auto-injected into subsequent commands — no need to parse and pass session IDs
• NDJSON output: One JSON result per line: {"index": 0, "command": "...", "success": true, "result": {...}}
• --stop-on-error: Exit on first failure (default: continue all)
• --session <id>: Pre-set session ID for all commands (skip session.open)

Input formats:

• JSON array from file: excelcli -q batch --input commands.json
• NDJSON from stdin: Get-Content commands.ndjson | excelcli -q batch

CLI Command Reference

Auto-generated from excelcli --help. Use these exact parameter names.

calculationmode

Control Excel recalculation (automatic vs manual). Set manual mode before bulk writes for faster performance, then recalculate once at the end.

Actions: get-mode, set-mode, calculate

chart

Chart lifecycle - create, read, move, and delete embedded charts. POSITIONING (choose one): - targetRange (PREFERRED): Cell range like 'F2:K15' — positions chart within cells, no point math needed. - left/top: Manual positioning in points (72 points = 1 inch). - Neither: Auto-positions chart below all existing content (used range + other charts). COLLISION DETECTION: All create/move/fit-to-range operations automatically check for overlaps with data and other charts. Warnings are returned in the result message if collisions are detected. Always verify layout with screenshot(capture-sheet) after creating charts. CHART TYPES: 70+ types available including Column, Line, Pie, Bar, Area, XY Scatter. CREATE OPTIONS: - create-from-range: Create from cell range (e.g., 'A1:D10') - create-from-table: Create from Excel Table (uses table's data range) - create-from-pivottable: Create linked PivotChart Use chartconfig for series, titles, legends, styles, placement mode.

Actions: list, read, create-from-range, create-from-table, create-from-pivottable, delete, move, fit-to-range

chartconfig

Chart configuration - data source, series, type, title, axis labels, legend, and styling. SERIES MANAGEMENT: - add-series: Add data series with valuesRange (required) and optional categoryRange - remove-series: Remove series by 1-based index - set-source-range: Replace entire chart data source TITLES AND LABELS: - set-title: Set chart title (empty string hides title) - set-axis-title: Set axis labels (Category, Value, CategorySecondary, ValueSecondary) CHART STYLES: 1-48 (built-in Excel styles with different color schemes) DATA LABELS: Show values, percentages, series/category names. Positions: Center, InsideEnd, InsideBase, OutsideEnd, BestFit. TRENDLINES: Linear, Exponential, Logarithmic, Polynomial (order 2-6), Power, MovingAverage. PLACEMENT MODE: - 1: Move and size with cells - 2: Move but don't size with cells - 3: Don't move or size with cells (free floating) Use chart for lifecycle operations (create, delete, move, fit-to-range).

Actions: set-source-range, add-series, remove-series, set-chart-type, set-title, set-axis-title, get-axis-number-format, set-axis-number-format, show-legend, set-style, set-placement, set-data-labels, get-axis-scale, set-axis-scale, get-gridlines, set-gridlines, set-series-format, list-trendlines, add-trendline, delete-trendline, set-trendline

conditionalformat

Conditional formatting - visual rules based on cell values. TYPES: cellValue (requires operatorType+formula1), expression (formula only). Both camelCase and kebab-case accepted. FORMAT: interiorColor/fontColor as #RRGGBB, fontBold/Italic, borderStyle/Color. OPERATORS: equal, notEqual, greater, less, greaterEqual, lessEqual, between, notBetween. For 'between' and 'notBetween', both formula1 and formula2 are required.

Actions: add-rule, clear-rules

connection

Data connections (OLEDB, ODBC, ODC import). TEXT/WEB/CSV: Use powerquery instead. Power Query connections auto-redirect to powerquery. TIMEOUT: 30 min auto-timeout for refresh/load-to.

Actions: list, view, create, refresh, delete, load-to, get-properties, set-properties, test

datamodel

Data Model (Power Pivot) - DAX measures and table management. CRITICAL: WORKSHEET TABLES AND DATA MODEL ARE SEPARATE! - After table append changes, Data Model still has OLD data - MUST call refresh to sync changes - Power Query refresh auto-syncs (no manual refresh needed) PREREQUISITE: Tables must be added to the Data Model first. Use table add-to-datamodel for worksheet tables, or powerquery to import and load data directly to the Data Model. DAX MEASURES: - Create with DAX formulas like 'SUM(Sales[Amount])' - DAX formulas are auto-formatted on CREATE/UPDATE via Dax.Formatter (SQLBI) - Read operations return raw DAX as stored DAX EVALUATE QUERIES: - Use evaluate to execute DAX EVALUATE queries against the Data Model - Returns tabular results from queries like 'EVALUATE TableName' - Supports complex DAX: SUMMARIZE, FILTER, CALCULATETABLE, TOPN, etc. DMV (DYNAMIC MANAGEMENT VIEW) QUERIES: - Use execute-dmv to query Data Model metadata via SQL-like syntax - Syntax: SELECT * FROM $SYSTEM.SchemaRowset (ONLY SELECT * supported) - Use DISCOVER_SCHEMA_ROWSETS to list all available DMVs Use datamodelrel for relationships between tables.

Actions: list-tables, list-columns, read-table, read-info, list-measures, read, delete-measure, delete-table, rename-table, refresh, create-measure, update-measure, evaluate, execute-dmv

datamodelrelationship

Data Model relationships - link tables for cross-table DAX calculations. CRITICAL: Deleting or recreating tables removes ALL their relationships. Use list-relationships before table operations to backup, then recreate relationships after schema changes. RELATIONSHIP REQUIREMENTS: - Both tables must exist in the Data Model first - Columns must have compatible data types - fromTable/fromColumn = many-side (detail table, foreign key) - toTable/toColumn = one-side (lookup table, primary key) ACTIVE VS INACTIVE: - Only ONE active relationship can exist between two tables - Use active=false when creating alternative paths - DAX USERELATIONSHIP() activates inactive relationships

Actions: list-relationships, read-relationship, create-relationship, update-relationship, delete-relationship

diag

Diagnostic commands for testing CLI/MCP infrastructure without Excel. These commands validate parameter parsing, routing, JSON serialization, and error handling — no Excel COM session needed.

Actions: ping, echo, validate-params

namedrange

Named ranges for formulas/parameters. CREATE/UPDATE: value is cell reference (e.g., 'Sheet1!$A$1'). WRITE: value is data to store. TIP: range(rangeAddress=namedRangeName) for bulk data read/write.

Actions: list, write, read, update, create, delete

pivottable

PivotTable lifecycle management: create from various sources, list, read details, refresh, and delete. Use pivottablefield for field operations, pivottablecalc for calculated fields and layout. BEST PRACTICE: Use 'list' before creating. Prefer 'refresh' or field modifications over delete+recreate. Delete+recreate loses field configurations, filters, sorting, and custom layouts. REFRESH: Call 'refresh' after configuring fields with pivottablefield to update the visual display. This is especially important for OLAP/Data Model PivotTables where field operations are structural only and don't automatically trigger a visual refresh. CREATE OPTIONS: - 'create-from-range': Use source sheet and range address for data range - 'create-from-table': Use an Excel Table (ListObject) as source - 'create-from-datamodel': Use a Power Pivot Data Model table as source

Actions: list, read, create-from-range, create-from-table, create-from-datamodel, delete, refresh

pivottablecalc

PivotTable calculated fields/members, layout configuration, and data extraction. Use pivottable for lifecycle, pivottablefield for field placement. CALCULATED FIELDS (for regular PivotTables): - Create custom fields using formulas like '=Revenue-Cost' or '=Quantity*UnitPrice' - Can reference existing fields by name - After creating, use pivottablefield add-value-field to add to Values area - For complex multi-table calculations, prefer DAX measures with datamodel CALCULATED MEMBERS (for OLAP/Data Model PivotTables only): - Create using MDX expressions - Member types: Member, Set, Measure LAYOUT OPTIONS: - 0 = Compact (default, fields in single column) - 1 = Tabular (each field in separate column - best for export/analysis) - 2 = Outline (hierarchical with expand/collapse)

Actions: get-data, create-calculated-field, list-calculated-fields, delete-calculated-field, list-calculated-members, create-calculated-member, delete-calculated-member, set-layout, set-subtotals, set-grand-totals

pivottablefield

PivotTable field management: add/remove/configure fields, filtering, sorting, and grouping. Use pivottable for lifecycle, pivottablecalc for calculated fields and layout. IMPORTANT: Field operations modify structure only. Call pivottable refresh after configuring fields to update the visual display, especially for OLAP/Data Model PivotTables. FIELD AREAS: - Row fields: Group data by categories (add-row-field) - Column fields: Create column headers (add-column-field) - Value fields: Aggregate numeric data with Sum, Count, Average, etc. (add-value-field) - Filter fields: Add report-level filters (add-filter-field) AGGREGATION FUNCTIONS: Sum, Count, Average, Max, Min, Product, CountNumbers, StdDev, StdDevP, Var, VarP GROUPING: - Date fields: Group by Days, Months, Quarters, Years (group-by-date) - Numeric fields: Group by ranges with start/end/interval (group-by-numeric) NUMBER FORMAT: Use US format codes like '#,##0.00' for currency or '0.00%' for percentages.

Actions: list-fields, add-row-field, add-column-field, add-value-field, add-filter-field, remove-field, set-field-function, set-field-name, set-field-format, set-field-filter, sort-field, group-by-date, group-by-numeric

powerquery

Power Query M code and data loading. TEST-FIRST DEVELOPMENT WORKFLOW (BEST PRACTICE): 1. evaluate - Test M code WITHOUT persisting (catches syntax errors, validates sources, shows data preview) 2. create/update - Store VALIDATED query in workbook 3. refresh/load-to - Load data to destination Skip evaluate only for trivial literal tables. IF CREATE/UPDATE FAILS: Use evaluate to get the actual M engine error message, fix code, retry. DATETIME COLUMNS: Always include Table.TransformColumnTypes() in M code to set column types explicitly. Without explicit types, dates may be stored as numbers and Data Model relationships may fail. DESTINATIONS: 'worksheet' (default), 'data-model' (for DAX), 'both', 'connection-only'. Use 'data-model' to load to Power Pivot, then use datamodel to create DAX measures. TARGET CELL: targetCellAddress places tables without clearing sheet. TIMEOUT: 30 min auto-timeout for refresh and load-to. For quick queries, use timeout=60 or similar. timeout=0 or omitted uses the 30 min default.

Actions: list, view, refresh, get-load-config, delete, create, update, load-to, refresh-all, rename, unload, evaluate

range

Core range operations: get/set values and formulas, copy ranges, clear content, and discover data regions. Use rangeedit for insert/delete/find/sort. Use rangeformat for styling/validation. Use rangelink for hyperlinks and cell protection. Calculation mode and explicit recalculation are handled by calculationmode. BEST PRACTICE: Use 'get-values' to check existing data before overwriting. Use 'clear-contents' (not 'clear-all') to preserve cell formatting when clearing data. set-values preserves existing formatting; use set-number-format after if format change needed. DATA FORMAT: values and formulas are 2D JSON arrays representing rows and columns. Example: [[row1col1, row1col2], [row2col1, row2col2]] Single cell returns [[value]] (always 2D). REQUIRED PARAMETERS: - sheetName + rangeAddress for cell operations (e.g., sheetName='Sheet1', rangeAddress='A1:D10') - For named ranges, use sheetName='' (empty string) and rangeAddress='MyNamedRange' COPY OPERATIONS: Specify source and target sheet/range for copy operations. NUMBER FORMATS: Use US locale format codes (e.g., '#,##0.00', 'mm/dd/yyyy', '0.00%').

Actions: get-values, set-values, get-formulas, set-formulas, validate-formulas, clear-all, clear-contents, clear-formats, copy, copy-values, copy-formulas, get-number-formats, set-number-format, set-number-formats, get-used-range, get-current-region, get-info

rangeedit

Range editing operations: insert/delete cells, rows, and columns; find/replace text; sort data. Use range for values/formulas/copy/clear operations. INSERT/DELETE CELLS: Specify shift direction to control how surrounding cells move. - Insert: 'Down' or 'Right' - Delete: 'Up' or 'Left' INSERT/DELETE ROWS: Use row range like '5:10' to insert/delete rows 5-10. INSERT/DELETE COLUMNS: Use column range like 'B:D' to insert/delete columns B-D. FIND/REPLACE: Search within the specified range with optional case/cell matching. - Find returns up to 10 matching cell addresses with total count. - Replace modifies all matches by default. SORT: Specify sortColumns as array of {columnIndex: 1, ascending: true} objects. Column indices are 1-based relative to the range.

Actions: insert-cells, delete-cells, insert-rows, delete-rows, insert-columns, delete-columns, find, replace, sort

rangeformat

Range formatting operations: apply styles, set fonts/colors/borders, add data validation, merge cells, auto-fit dimensions. Use range tool for values/formulas/copy/clear operations. set-style: Apply a named Excel style (Heading 1, Good, Bad, Neutral, Normal). Best for semantic status labels (Good/Bad/Neutral have fill colours and are theme-aware) and document hierarchy (Heading 1/2/3). NOTE: Heading styles do NOT apply a fill colour — use format-range when you need a coloured header row. format-range: Apply any combination of bold, fillColor, fontColor, alignment, borders. Required whenever you need a fill colour or custom branding. Pass ALL desired properties in a SINGLE call — do not call format-range multiple times for the same range. format-ranges: Apply one shared formatting payload to multiple ranges on the same worksheet. Prefer this over repeated format-range calls when the same styling applies to multiple non-contiguous targets. All target ranges are validated before formatting begins. If any target range is invalid, nothing is formatted. COLORS: Hex '#RRGGBB' (e.g., '#FF0000' for red, '#00FF00' for green) FONT: size in points (e.g., 12, 14, 16), alignment: 'left', 'center', 'right' / 'top', 'middle', 'bottom' DATA VALIDATION: Restrict cell input with validation rules: - Types: 'list', 'whole', 'decimal', 'date', 'time', 'textLength', 'custom' - For list validation, formula1 is the list source (e.g., '=$A$1:$A$10' or '"Option1,Option2,Option3"') - Operators: 'between', 'notBetween', 'equal', 'notEqual', 'greaterThan', 'lessThan', 'greaterThanOrEqual', 'lessThanOrEqual' MERGE: Combines cells into one. Only top-left cell value is preserved.

Actions: set-style, get-style, format-range, format-ranges, validate-range, get-validation, remove-validation, auto-fit-columns, auto-fit-rows, merge-cells, unmerge-cells, get-merge-info, set-column-width, set-row-height

…(truncated)