It gives the assistant a configured way to access spreadsheet files without requiring the server to be installed directly on the host. The description does not specify the server's individual spreadsheet operations.

agent-spreadsheet — MCP server by PSU3D0

agent-spreadsheet

agent-spreadsheet is an MCP server for Claude Code from PSU3D0/agent-spreadsheet. Its token cost is not measured, scanned A, original, Apache-2.0.

An MCP server for working with spreadsheet files, configured to run in Docker. MCP is a connection format that lets an assistant call an external tool; this server mounts a workbook directory into the container.

In plain words

What is it for?: Use it when an assistant needs to connect to the configured spreadsheet service and work with files in the supplied workbook directory.
Why use it?: It gives the assistant a configured way to access spreadsheet files without requiring the server to be installed directly on the host. The description does not specify the server's individual spreadsheet operations.

Written for Claude Code: shipped in a Claude Code plugin.

Part of the formualizer plugin — 1 skill, 1 MCP server shipped together

Good fit Use it when an assistant needs to connect to the configured spreadsheet service and work with files in the supplied workbook directory.

Compare 6 mcp servers from other repositories ↓

Install with agentmods

npx agentmods add mcp/psu3d0/agent-spreadsheet/formualizer-agent-spreadsheet

Install

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.

Clone the repo

git clone --depth 1 https://github.com/PSU3D0/agent-spreadsheet

Made for: Claude Code.

Or install formualizer, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/psu3d0/agent-spreadsheet/formualizer-agent-spreadsheet/github.svg)](https://agentmods.dev/mcp/psu3d0/agent-spreadsheet/formualizer-agent-spreadsheet)

Your own site

<a href="https://agentmods.dev/mcp/psu3d0/agent-spreadsheet/formualizer-agent-spreadsheet"><img src="https://agentmods.dev/badge/mcp/psu3d0/agent-spreadsheet/formualizer-agent-spreadsheet/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.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/psu3d0/agent-spreadsheet/formualizer-agent-spreadsheet"><img src="https://agentmods.dev/badge/mcp/psu3d0/agent-spreadsheet/formualizer-agent-spreadsheet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

agent-spreadsheet 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 2d 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.

plugins/formualizer/server.json · 16 lines

What it actually says

{
  "agent-spreadsheet": {
    "command": "docker",
    "args": [
      "run",
      "-i",
      "--rm",
      "ghcr.io/psu3d0/agent-spreadsheet:0.16.0-full",
      "-i",
      "--rm",
      "-v",
      "{workbook_dir}:/data"
    ],
    "env": {}
  }
}

Changes

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.

2d ago First seen · 16 lines scan A 480ced64f575

Subscribe to this mod's changes

agent-spreadsheet is an MCP server published in the GitHub repository PSU3D0/agent-spreadsheet (64 stars, last pushed yesterday), licensed Apache-2.0. 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 2026-11-10.

Documents Spreadsheets spreadsheet spreadsheet-agent spreadsheet-ai spreadsheet-mcp

agent-spreadsheet next to 6 mcp servers from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-spreadsheetPSU3D0/agent-spreadsheet	MCP server	64	yesterday	Apache-2.0	A	—	Claude Code
logisheets-mcplogisky/logisheets-mcp	MCP server	41	1mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
servalsheetskhill1269/servalsheets	MCP server	0	1mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
numera-mcpvectojs/numera-mcp	MCP server	0	2mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
wisegrid-mcpRyanKramer/wisegrid-mcp	MCP server	0	2mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
excel-mcp-serverharis-musa/excel-mcp-server	MCP server	4.3k	2d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
crepe-mcpmariolpantunes/crepe-mcp	MCP server	2	5d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode