Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/dosev-ai/mcp-officeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/dosev-ai/mcp-office/mcp-office-excel)<a href="https://agentmods.dev/mcp/dosev-ai/mcp-office/mcp-office-excel"><img src="https://agentmods.dev/badge/mcp/dosev-ai/mcp-office/mcp-office-excel/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/dosev-ai/mcp-office/mcp-office-excel"><img src="https://agentmods.dev/badge/mcp/dosev-ai/mcp-office/mcp-office-excel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-office-excel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"mcp-office-excel": {
"command": "uvx",
"args": [
"mcp-office",
"mcp-office",
"excelmcp"
],
"env": {
"EXCEL_ALLOWLIST_ROOTS": "",
"EXCEL_ENABLE_WRITE": "",
"EXCEL_ENABLE_COM": "",
"EXCEL_MAX_ITEMS": ""
}
}
}What else server.json configures
This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 16 lines scan A 47bd9fd92213
mcp-office-excel is an MCP server published in the GitHub repository dosev-ai/mcp-office (7 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
google-sheets
MCP server "google-sheets" as configured in ringo380/claude-google-sheets-mcp. Runs claude_google_sheets.server with /path/to/claude-google-sheets-mcp/venv/bin/python.
mcp-server-excel
MCP server "mcp-server-excel" as configured in sbroenne/mcp-server-excel. Launched with Sbroenne.ExcelMcp.McpServer.
logisheets-mcp
An Excel-compatible spreadsheet engine for agents: deterministic formulas, block memory, real .xlsx. Runs locally from the logisheets-mcp npm package. Needs 1 environment variable to run.
excel-vision-mcp
MCP Server for reading and writing Excel files with embedded image extraction. The first MCP that lets AI agents SEE images inside your spreadsheets. Runs locally from the excel-vision-mcp Python package.
excel
MCP server "excel" as configured in TangentDomain/excel-mcp-server. Runs locally from the . Python package. Needs 2 environment variables to run.
localdata-mcp
MCP server for databases, spreadsheets, structured files, and directed graphs. Runs locally from the localdata-mcp Python package.