Excel (npm) MCP Server

mcp-excel npm v0.1.0

Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.

让 AI 助手直接读写本地 Excel 文件的 MCP 服务（支持 xls / xlsx / csv）

View on npm ↗ Raw report (JSON) ↗

Trust grade

98/100

Last scanned 2026-09-07 get badge →

Trust

A · 98/100

Adoption risk for you: the threat score, then adjusted down for blast radius, publisher verification and how much the scan could see. Deterministic; every point is auditable.

Capability

Minimal

Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.

Coverage

Source

How much the scan could actually inspect. Shallow coverage is stated, never hidden.

A Why this grade threat 100 − adoption risk = 98/100

The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.

1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:

The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.

2. Client adoption risk — 100 − 2 = 98. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:

Points	Adoption-risk factor
−2	publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read

Capability observations and info notes are shown under Findings but never scored. Open any row's finding below for the file, line and evidence behind a deduction.

Findings 0

✓ No findings. The scan raised nothing on this surface — see Coverage for how deep it could look.

Tools 15

Each tool and what it can reach — statically extracted from the published source.

add_sheetno sensitive capability
create_workbookno sensitive capability
dedupe_rangeno sensitive capability
delete_sheetno sensitive capability
filter_rangeno sensitive capability
format_cellsno sensitive capability
insert_imageno sensitive capability
list_sheetsno sensitive capability
merge_cellsno sensitive capability
read_rangeno sensitive capability

Show 5 more tools ↓

rename_sheetno sensitive capability
set_dimensionsno sensitive capability
set_formulano sensitive capability
sort_rangeno sensitive capability
write_rangeno sensitive capability

What this scan could not see

Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Versions 1

Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.

Version	Score	Findings	Engine	Scanned
`v0.1.0` latest	A 98/100	0	1.13.0	2026-09-07

Embed this score

Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.

Markdown (GitHub README)

[![MCP Trust Score](https://mcptrustchecker.com/registry/mcp-excel/badge.svg)](https://mcptrustchecker.com/registry/mcp-excel)

HTML

<a href="https://mcptrustchecker.com/registry/mcp-excel"><img src="https://mcptrustchecker.com/registry/mcp-excel/badge.svg" alt="MCP Trust Score" height="20"></a>

Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/mcp-excel/badge.json via https://img.shields.io/endpoint?url=…

Verify this score yourself

The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.

npx mcptrustchecker scan mcp-excel --online

Use the free API → How scoring works

Other implementations of Excel 10

Independent packages implementing the same tool, scanned with the same engine. Compare all 11 side by side →

Excel (zhiweixu) npm

@zhiweixu/excel-mcp-server

Excel file processing server based on Model Context Protocol (MCP)

Other Score 99/100 0 findings 83/wk Cap. Minimal

Excel (choco9527) npm

excel-mcp

基于 MCP 协议的 Excel/CSV 文件读取服务

Other Score 99/100 0 findings 57/wk Cap. Minimal

Excel (shmaxi) npm

@shmaxi/excel-mcp-server

Excel MCP Server for manipulating Excel files - Node.js implementation

Files & Storage Score 99/100 0 findings 31/wk Cap. Minimal

Excel (yzfly) PyPI

mcp-excel-server

MCP Excel Server for Excel operations through the Model Context Protocol

Other Score 99/100 0 findings Cap. Minimal

Excel (itkmoon) npm

@itkmoon/excel-mcp

A powerful MCP tool for Excel file operations with read, write, and formatting capabilities

Developer Tools Score 98/100 0 findings 15/wk Cap. Minimal

Excel (PyPI) PyPI

excel-mcp-server

Excel MCP Server for manipulating Excel files

AI & Agents Score 98/100 0 findings Cap. Minimal

More in AI & Agents

Agent Source verified npm

@aauth/mcp-agent

Authenticated MCP transport with HTTP Signatures for AAuth agents

AI & Agents Score 100/100 1 finding 1.4k/wk Cap. Minimal

Agent Claim Source verified npm

@vk0/agent-claim-mcp

Local-first MCP server for parallel AI coding agents to claim file ownership before edits, preventing stomping on each other in the same worktree.

AI & Agents Score 100/100 0 findings 66/wk Cap. Minimal

Agent Comm Source verified npm

agent-comm

Agent-agnostic intercommunication system — sessions, messaging, channels, shared state, and real-time events

AI & Agents Score 100/100 2 findings 159/wk Cap. Minimal

Agent Comm Source verified npm

@jerfowler/agent-comm-mcp-server

MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility

AI & Agents Score 100/100 0 findings 17/wk Cap. Minimal

Agent Mcp Manager Source verified npm

agent-mcp-manager

Programmatic add/link/unlink for MCP servers across 23 AI coding agents (Claude Code, Claude Desktop, Cursor, VS Code, Codex, Gemini CLI, Zed, Cline, OpenCode, Goose, Kiro, Windsurf, and more). Functional API with dry-run support.

AI & Agents Score 100/100 0 findings 234/wk Cap. Minimal

Agent Mesh Source verified npm

@reaatech/agent-mesh-mcp-server

MCP server layer exposing agent-mesh orchestrator as an MCP agent

AI & Agents Score 100/100 0 findings 9/wk Cap. Minimal