MCP Server Spreadsheet

by marekrost Your server? Claim it

local only

MCP Server Spreadsheet runs on your own machine — the client starts it, so there is no endpoint to ping. 107 installs a week from pypi. Last commit 11 Aug 2026.

MCP server for spreadsheet files (.xlsx, .csv, .ods) - cell-level ops + DuckDB SQL engine.

Installs per day peak 45 · avg 21 · -24% w/w

a month agotoday

107

Installs / week

pypi · mcp-server-spreadsheet

Stars

0 open issues

11 Aug 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check MCP Server Spreadsheet every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp-server-spreadsheet -- uvx mcp-server-spreadsheet

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-server-spreadsheet": {
      "command": "uvx",
      "args": [
        "mcp-server-spreadsheet"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp-server-spreadsheet]
command = "uvx"
args = ["mcp-server-spreadsheet"]

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server-spreadsheet": {
      "command": "uvx",
      "args": [
        "mcp-server-spreadsheet"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp-server-spreadsheet": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-server-spreadsheet"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: MCP_SPREADSHEET_ROOT (Optional. Absolute path to a directory; all tool path arguments are restricted to this tree. Unset = no restriction).

Alternatives to MCP Server Spreadsheet

same job, measured the same way

slim-sheet

by j4flmao

Spreadsheet MCP for any agent: reads xlsx/xls/ods/csv, SQL, cleaning, formulas, safe edits

517 installs/wk local only

Text Spreadsheet

by demos-ra

Read and filter Excel, ODS, CSV, SQLite, Parquet and MTSV files — or a directory — as plain text

178 installs/wk local only

MCP Trino

by tuannvm

MCP server for Trino distributed SQL query engine access

local only

tableski

by yarenty

Every spreadsheet is a table: Excel, CSV, Parquet and JSON as SQL tables for AI agents.

answering

Universal DB MCP

by fashad-ahmed

Security-first MCP server for PostgreSQL, SQLite, MySQL, DuckDB with SQL injection prevention.

89 installs/wk local only

SQL Safe MCP

by proprock

Minimal, read-only, PII-safe MCP server for SQL databases.

211 installs/wk local only

Mysql

by marcelo-ochoa

An MCP server for MySQL databases.

101 installs/wk local only

Pipetable

by melihbirim

Local data runtime for AI agents: query CSV, Excel, Parquet and JSON files with DuckDB SQL.

local only

MCP Server Spreadsheet — questions

Answers built from our own checks of this server.

Why is there no uptime for MCP Server Spreadsheet?

MCP Server Spreadsheet runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package mcp-server-spreadsheet was installed 107 times last week.

How do I connect MCP Server Spreadsheet?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls mcp-server-spreadsheet straight from pypi; nothing to host, nothing to sign up for.

How many people use MCP Server Spreadsheet?

The pypi package mcp-server-spreadsheet was installed 107 times in the last week. Week over week that is -24%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is MCP Server Spreadsheet open source?

Yes — it is published under the MIT licence, written in Python and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.