Xlsx Audit Mcp

io.github.arose26Published by GitHub account arose26v0.1.0Updated Nov 3, 2026

Audit Excel workbooks: formula dependency tracing, circular references, risk smells. Local only.

The publisher's own server: audit.domains - Domain Valuation

VerifiedSTDIODesktop onlyDeveloper ToolsData & Analytics

Overview

AI-generated overview

Local MCP server that audits Excel workbooks: traces formula precedents and dependents, flags circular references and risky formula patterns.

What you can do
  • Summarize a workbook: sheets, dimensions, formula counts, defined names and external links
  • List formulas with cell addresses and cached values, filterable by function such as INDIRECT or VLOOKUP
  • Trace a single cell's formula, value, precedents and dependents, including cells that reach it through ranges
  • Run a whole-model audit with a ranked risk report covering circular references, volatile functions, hardcoded constants, external links, merged cells and very long formulas
When to use it
Useful when reviewing or debugging a spreadsheet model rather than editing it: asking what feeds a total, what breaks if an assumption changes, or whether a workbook looks fragile before it is relied on.
Requirements
Runs as a local process over stdio, installed from the npm package xlsx-audit-mcp (typically via npx), so Node.js and npm are needed. Desktop client only; no authentication, API keys or environment variables are declared. Reads local .xlsx files.
Before you install
It reads local workbook files, so the assistant can see their contents, though the README states nothing leaves the machine. It does not evaluate formulas and shows cached values instead, and R1C1 notation and structured table references are counted but not resolved, so results can be incomplete. It is read-only auditing, not editing.

Installation

In SourceWeft

  1. Open Xlsx Audit Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

xlsx-audit-mcp

An MCP server that audits Excel workbooks. Other Excel MCP servers read and write your data — this one reviews your model:

  • "What feeds the Total cell on the Summary sheet?" — precedent tracing
  • "If I change this assumption, what breaks?" — dependent tracing, including cells that consume it through ranges like SUM(A1:A40)
  • "Audit this workbook" — circular references with example chains, volatile functions (INDIRECT, OFFSET, NOW, RAND...), hardcoded constants buried inside formulas, external workbook links, merged cells, extra-long formulas

Spreadsheet mistakes are famously expensive. This is the "trace precedents" discipline auditors apply by hand, exposed to an LLM for a whole workbook at once. Local files only; nothing leaves your machine.

Quick start

Claude Code

bash
claude mcp add xlsx-audit -- npx -y xlsx-audit-mcp

Claude Desktop — add to claude_desktop_config.json:

json
{  "mcpServers": {    "xlsx-audit": {      "command": "npx",      "args": ["-y", "xlsx-audit-mcp"]    }  }}

Then: "Audit C:\models\budget-2026.xlsx and tell me what looks fragile."

Tools

ToolWhat it does
workbook_overviewSheets, dimensions, formula counts, defined names, external links
list_formulasFormulas with addresses and cached values, filterable (INDIRECT, VLOOKUP, ...)
trace_cellOne cell's formula, value, precedents, and dependents (direct + via ranges)
audit_workbookRanked risk report across the whole model

How it works

  • Reference tokenizer that understands real formulas: string literals are stripped first (the "A1" in INDIRECT("A1") is not a reference), function names can't collide (the G10 in LOG10(...) is not a cell), $ absolutes, quoted sheet names ('My Data'!A1), and ranges are handled.
  • Shared formulas are materialized. Excel stores filled formulas once with an offset scheme; the loader translates them per-cell (relative refs shifted, absolutes preserved), so dependency queries see what each cell actually computes.
  • Ranges are never expanded for storage — dependents queries use range-containment tests, and cycle detection caps range fan-out (a SUM(A:A) can't explode the graph; capped ranges are reported, not silently dropped).
  • No formula evaluation. Cached values from the file are shown instead — no spreadsheet engine dependency.

Known limitations: R1C1 notation and structured table references ([@Column]) are counted but not resolved into the graph.

Development

bash
npm installnpm test                 # offline tests — synthetic workbooks built in-suitenpm run build            # tsc → dist/node scripts/smoke.mjs   # end-to-end: generates a workbook, drives the server over stdio

Architecture: src/xlsx.ts (zip + XML → workbook model) and src/formulas.ts (tokenizer, graph, smells) are pure logic; src/index.ts is the MCP wiring.

License

MIT

Source: README.md at commit ba65234

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Audit integrations