Audit Excel workbooks: formula dependency tracing, circular references, risk smells. Local only.
MCPpedia last refreshed this data
io.github.arose26/xlsx-audit-mcp is an MCP server that audit Excel workbooks: formula dependency tracing, circular references, risk smells. Local only. Its tool list has not been published yet over stdio and sse, requires no API key, and scores 85/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"xlsx-audit": {
"args": [
"-y",
"xlsx-audit-mcp"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
An MCP server that audits Excel workbooks. Other Excel MCP servers read and write your data — this one reviews your model:
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'xlsx-audit-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked xlsx-audit-mcp against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in productivity
Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.
MCP server for monday.com integration.
Give AI agents access to your Obsidian vault via local files or Self-hosted LiveSync.
An MCP server to extend the context of agents. Useful when coding big features or vibe coding and need to store/recall progress, key moments or changes or anything worth remembering. Simply ask the agent to store memories and recall whenever you want.
MCP Security Weekly
Get CVE alerts and security updates for io.github.arose26/xlsx-audit-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
An MCP server that audits Excel workbooks. Other Excel MCP servers read and write your data — this one reviews your model:
SUM(A1:A40)INDIRECT, OFFSET, NOW, RAND...), hardcoded constants buried inside formulas, external workbook links, merged cells, extra-long formulasSpreadsheet 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.
Claude Code
claude mcp add xlsx-audit -- npx -y xlsx-audit-mcp
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"xlsx-audit": {
"command": "npx",
"args": ["-y", "xlsx-audit-mcp"]
}
}
}
Then: "Audit C:\models\budget-2026.xlsx and tell me what looks fragile."
| Tool | What it does |
|---|---|
workbook_overview | Sheets, dimensions, formula counts, defined names, external links |
list_formulas | Formulas with addresses and cached values, filterable (INDIRECT, VLOOKUP, ...) |
trace_cell | One cell's formula, value, precedents, and dependents (direct + via ranges) |
audit_workbook | Ranked risk report across the whole model |
"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.SUM(A:A) can't explode the graph; capped ranges are reported, not silently dropped).Known limitations: R1C1 notation and structured table references ([@Column]) are counted but not resolved into the graph.
npm install
npm test # offline tests — synthetic workbooks built in-suite
npm 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.
MIT