excel
Author and run Excel VBA macros via COM. action='runvba' writes a macro into a managed Trusted Location and runs it; action='checkaccessvbom' is a read-only preflight. Runs VBA where formula-only tools cannot. One-time setup: node scripts/enable-access-vbom.mjs.
How to use it
excel is exposed by the Desktop Touch MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the excel tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Desktop Touch MCP
npx -y @harusame64/desktop-touch-mcpOther tools in Desktop Touch MCP (15)
Deep inspection via js (scripting), dom (HTML), and appState (SPA data extraction).
Legacy UIA-based click by name/ID (fallback when entities are unavailable).
Perform actions (click, type, drag, select) on entities via lease validation. Returns semantic diffs — plus an optional roiCapture (changed-region PNG + next-target preview) on visual-only targets.
Observe the desktop. Returns interactive entities with leases (UIA, CDP, Terminal, Visual SoM).
Lightweight check of focus, active window, cursor, and Auto-Perception attention signal.
Manage credentials the terminal autofills for you (SSH key passphrases, sudo / login passwords). Secrets are entered once into the locker's own secure dialog and stored encrypted on this machine (Windows DPAPI); they are never shown to the assistant. action='launchconsole' opens an autofill-capable
Send keyboard input. Supports background input (WMCHAR) and IME-safe clipboard bypass.
Batch up to 50 operations into a single round-trip for maximum efficiency.
Multi-mode capture: detail='text' (UIA/OCR), diffMode (P-frame), dotByDot (1:1), and background. Returns a cheap screenshot://by-ref/{id} link to the saved image instead of inlining pixels every time.
Multi-strategy: raw (notches), toelement, smart (virtual lists), and capture (stitch).
Diagnostic check for native engine health and feature activation.
Unified command execution: run (send + wait + read), read (OCR/UIA), and send. run completion modes: quiet, pattern, and exit (waits for the command to finish + returns its exit code — see Terminal command completion).
Efficient server-side polling for window, focus, text, or URL state changes.
Launch apps and auto-detect new HWNDs (supports localized titles).
Instant session orientation: all window thumbnails + UI summaries in one call.