No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by negokaz · MCP Server · ★ 1.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is excel-mcp-server safe to install? View the security audit →
Featured in: Spreadsheet & Excel AI Tools
Excel MCP Server A Model Context Protocol (MCP) server that reads and writes MS Excel data. Features Read/Write text values Read/Write formulas Create new sheets 🪟Windows only: Live editing Capture screen image from a sheet For more details, see the tools section. Requirements Node.js 20.x or later Supported file formats xlsx (Excel book) xlsm (Excel macro-enabled book) xltx (Excel template) xltm (Excel macro-enabled template) Installation Installing via NPM excel-mcp-server is automatically installed by adding the following configuration to the MCP servers configuration. For Windows: For o
| Stars | 1,004 |
| Forks | 127 |
| Language | Go |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70.0927018831741/100 |
| Open Issues | 28 |
| Last Updated | 2025-07-19 |
| Created | 2025-02-16 |
| Platforms | go, mcp |
| Est. Tokens | ~64k |
Explore other popular mcp server tools:
excel-mcp-server is A Model Context Protocol (MCP) server that reads and writes MS Excel data. It is categorized as a MCP Server with 1.0k GitHub stars.
excel-mcp-server is primarily written in Go.
You can find installation instructions and usage details in the excel-mcp-server GitHub repository at github.com/negokaz/excel-mcp-server. The project has 1.0k stars and 127 forks, indicating an active community.
excel-mcp-server is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: